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

    Neuronpedia

    INDEX
    Explanations

    Formal/theoretical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]];
    -0.07
    -0.06
    .Panel
    -0.06
     آ
    -0.06
    )]
↵
    -0.06
    -0.06
    ’ye
    -0.06
     drifting
    -0.06
     spectrum
    -0.06
    -0.06
    POSITIVE LOGITS
     Philippe
    0.07
    τερα
    0.07
    거래가
    0.07
    ερι
    0.07
    umericUpDown
    0.07
    _HTTP
    0.06
    ουλίου
    0.06
     testcase
    0.06
     الملك
    0.06
    hyp
    0.06
    Act Density 0.039%

    No Known Activations