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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DialogInterface
    -0.07
    \Security
    -0.07
    (writer
    -0.07
     편집
    -0.07
    ]-'
    -0.06
     cnn
    -0.06
    ADV
    -0.06
    )findViewById
    -0.06
     OK
    -0.06
     careful
    -0.06
    POSITIVE LOGITS
    _TYPE
    0.07
    last
    0.07
    regexp
    0.07
     khoản
    0.07
    isle
    0.06
    lom
    0.06
    nuts
    0.06
    List
    0.06
     Lydia
    0.06
    resolve
    0.06
    Act Density 0.008%

    No Known Activations