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

    Neuronpedia

    INDEX
    Explanations

    code snippets/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breaker
    -0.07
    ��
    -0.07
    ่ม
    -0.06
    /M
    -0.06
    经过
    -0.06
     SELECT
    -0.06
     �
    -0.06
    initial
    -0.06
    anlık
    -0.06
    Lng
    -0.06
    POSITIVE LOGITS
     lei
    0.07
     vibrant
    0.06
    _stream
    0.06
    xdd
    0.06
     fizik
    0.06
    elfare
    0.06
     lem
    0.06
     mop
    0.06
     Slash
    0.06
    (frame
    0.06
    Act Density 0.043%

    No Known Activations