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

    Neuronpedia

    INDEX
    Explanations

    technical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACTION
    -0.06
     lamp
    -0.06
     hinges
    -0.06
    ’daki
    -0.06
    hp
    -0.06
    付
    -0.06
    Map
    -0.06
    /<?
    -0.06
    力
    -0.06
     nuestras
    -0.06
    POSITIVE LOGITS
     ignored
    0.08
    ือน
    0.06
    RESP
    0.06
     sexuality
    0.06
     GIR
    0.06
     raised
    0.06
     ویژ
    0.06
    UCH
    0.06
    rocessing
    0.06
    _da
    0.06
    Act Density 0.011%

    No Known Activations