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

    Neuronpedia

    INDEX
    Explanations

    depressive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝙥
    -0.07
    .Rest
    -0.07
    ,text
    -0.06
     JUST
    -0.06
     Red
    -0.06
     nội
    -0.06
    جيد
    -0.06
     hog
    -0.06
     пи
    -0.06
    are
    -0.06
    POSITIVE LOGITS
    羡
    0.08
    县公安局
    0.08
    diag
    0.07
    님
    0.07
    小微企业
    0.07
    묠
    0.07
    .delegate
    0.07
    婚纱
    0.07
    thren
    0.07
    שירה
    0.06
    Act Density 0.038%

    No Known Activations