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

    Neuronpedia

    INDEX
    Explanations

    academic achievement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mgr
    -0.08
    愤
    -0.07
    间
    -0.07
    剥离
    -0.06
    Studies
    -0.06
    ób
    -0.06
     ALS
    -0.06
    短信
    -0.06
    יפור
    -0.06
    _MIX
    -0.06
    POSITIVE LOGITS
     المدينة
    0.08
    .easing
    0.08
    .opengl
    0.07
    "';
    0.06
    abe
    0.06
    descricao
    0.06
     descriptive
    0.06
    ;c
    0.06
     villain
    0.06
     '"';↵
    0.06
    Act Density 0.044%

    No Known Activations