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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponents
    -0.07
     aes
    -0.06
    Slave
    -0.06
    $values
    -0.06
     leaned
    -0.06
     amis
    -0.06
     At
    -0.06
    स
    -0.06
     organizations
    -0.06
    _slave
    -0.06
    POSITIVE LOGITS
    _PRIV
    0.07
    :b
    0.07
    Blob
    0.06
    (dummy
    0.06
    を行
    0.06
    (['/
    0.06
     endforeach
    0.06
     解
    0.06
    .checkSelfPermission
    0.06
     CString
    0.06
    Act Density 0.000%

    No Known Activations