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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    推销
    -0.09
    ptive
    -0.07
     primitive
    -0.07
    outh
    -0.07
    ি�
    -0.07
    (setting
    -0.07
    ◄
    -0.07
     undesirable
    -0.07
    itory
    -0.07
    滟
    -0.07
    POSITIVE LOGITS
    _Buffer
    0.08
    煋
    0.08
    であり
    0.07
    .DEFAULT
    0.07
    隔离
    0.06
    不便
    0.06
    溚
    0.06
    有必要
    0.06
    jf
    0.06
    	bytes
    0.06
    Act Density 0.000%

    No Known Activations