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

    Neuronpedia

    INDEX
    Explanations

    are preceding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StudentNo
    0.46
     Nonlinear
    0.45
     Woodbridge
    0.45
    contentType
    0.45
     TCS
    0.44
     Truman
    0.44
    opio
    0.44
    messageInfo
    0.44
    vertebr
    0.43
     Conor
    0.43
    POSITIVE LOGITS
     else
    0.52
     ecz
    0.50
     אני
    0.49
    ai
    0.47
     оригинала
    0.47
     Elsewhere
    0.47
     academies
    0.46
     arises
    0.46
     fatalities
    0.46
     originals
    0.46
    Act Density 0.001%

    No Known Activations