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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⬊
    -0.07
     suit
    -0.07
     IDC
    -0.07
     labeled
    -0.07
    Indeed
    -0.06
     derby
    -0.06
     prerequisite
    -0.06
    подоб
    -0.06
    ﻏ
    -0.06
    _Position
    -0.06
    POSITIVE LOGITS
     شيء
    0.07
     carga
    0.07
     много
    0.07
    降幅
    0.07
    .jasper
    0.07
    .assertTrue
    0.07
    <float
    0.07
    Vals
    0.06
    empty
    0.06
     Mant
    0.06
    Act Density 0.193%

    No Known Activations