Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or desire for improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions indicating direction or location

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by location/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.27
    MLLoader
    -0.75
     незавершена
    -0.72
     الحره
    -0.67
     Meksiku
    -0.66
     دیکھیے
    -0.66
     })}
    -0.65
     PyTuple
    -0.65
    AlterField
    -0.64
    ]),
    -0.64
    POSITIVE LOGITS
    apunov
    0.68
    apatos
    0.58
    drucks
    0.57
     Versicher
    0.54
    nicity
    0.53
     kompeti
    0.53
    ardom
    0.53
    ToServer
    0.52
    anguardia
    0.52
    atég
    0.52
    Act Density 0.460%

    No Known Activations