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

    Neuronpedia

    INDEX
    Explanations

    crisis text line instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tigris
    0.81
    objClass
    0.73
     Apica
    0.70
    ᒋ
    0.69
     curva
    0.69
    馊
    0.69
     helix
    0.67
     الأح
    0.67
     agarose
    0.65
     Westfield
    0.65
    POSITIVE LOGITS
    cp
    0.64
    Defined
    0.62
    ˜</
    0.60
    僧
    0.59
    等於
    0.58
    Tone
    0.58
    टर
    0.56
     Defined
    0.56
    मान
    0.54
     फैल
    0.54
    Act Density 0.056%

    No Known Activations