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

    Neuronpedia

    INDEX
    Explanations

    dates in forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fuse
    -0.08
    ユ
    -0.07
    捐赠
    -0.07
    lever
    -0.07
    advance
    -0.07
    傳統
    -0.07
    dimensions
    -0.07
    intel
    -0.07
    posing
    -0.07
    Trad
    -0.07
    POSITIVE LOGITS
     ESL
    0.08
     pione
    0.07
    孤儿
    0.07
     accessor
    0.07
     Auschwitz
    0.07
    LIBINT
    0.07
    .onerror
    0.07
     Salvation
    0.07
    胆固醇
    0.07
    �
    0.07
    Act Density 0.007%

    No Known Activations