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

    Neuronpedia

    INDEX
    Explanations

    particularly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Santana
    -0.08
    qed
    -0.07
    くなり
    -0.07
    .department
    -0.07
     quatre
    -0.07
     antes
    -0.07
    웁
    -0.07
    climate
    -0.07
     USSR
    -0.07
     vp
    -0.06
    POSITIVE LOGITS
    _);↵↵
    0.07
    导弹
    0.07
    _BIN
    0.07
     Unable
    0.07
     dataArray
    0.07
     confer
    0.07
     đàn
    0.07
    からは
    0.07
    帜
    0.07
    /-
    0.07
    Act Density 0.003%

    No Known Activations