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

    Neuronpedia

    INDEX
    Explanations

    relevant terms and phrases pertaining to programming context and variable names

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

    texto Boton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jennings
    -0.54
    serialized
    -0.50
     MH
    -0.48
     Manning
    -0.47
     Camden
    -0.46
     Marshall
    -0.46
    MH
    -0.46
    msh
    -0.46
     Helms
    -0.46
    assen
    -0.46
    POSITIVE LOGITS
     HasFactory
    0.73
     Rückseite
    0.61
    avoit
    0.59
    ⎩
    0.58
     Flasche
    0.55
     Tiefe
    0.55
     Hälfte
    0.55
     bolsillo
    0.54
     ifrån
    0.52
     peuples
    0.51
    Act Density 0.004%

    No Known Activations