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

    Neuronpedia

    INDEX
    Explanations

    say .class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    58
    -0.07
    _background
    -0.07
    _client
    -0.07
     indent
    -0.06
    ฝ
    -0.06
     conforms
    -0.06
    領
    -0.06
     cache
    -0.06
    	send
    -0.06
    似
    -0.06
    POSITIVE LOGITS
     terör
    0.07
    ovel
    0.06
    .getCmp
    0.06
     ajud
    0.06
     juxtap
    0.06
     petits
    0.06
    taken
    0.06
     Wake
    0.06
    ghi
    0.06
    牛
    0.06
    Act Density 0.012%

    No Known Activations