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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, sites, or buildings

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

    places or locations

    np_acts-logits-general · gemini-2.0-flash

    locations and their prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.87
     незавершена
    -0.87
     defaultstate
    -0.81
     يتيمه
    -0.80
    AxisAlignment
    -0.78
    AutoScaleMode
    -0.75
    AndEndTag
    -0.75
    styleType
    -0.75
     wireType
    -0.74
     للمعارف
    -0.73
    POSITIVE LOGITS
     at
    0.84
     near
    0.84
     on
    0.82
     located
    0.82
     ubicada
    0.71
     downtown
    0.68
     off
    0.66
     ubicado
    0.66
    near
    0.66
     situés
    0.63
    Act Density 0.185%

    No Known Activations