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

    Neuronpedia

    INDEX
    Explanations

    Online forum activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comfortably
    -0.07
    _WRAPPER
    -0.07
     '{{
    -0.07
     Distributed
    -0.06
     सन
    -0.06
     dismissed
    -0.06
    httpClient
    -0.06
     الأح
    -0.06
    From
    -0.06
    models
    -0.06
    POSITIVE LOGITS
     Love
    0.07
     coercion
    0.06
     relent
    0.06
    Love
    0.06
    otate
    0.06
    ไล
    0.06
    ате
    0.06
     initiation
    0.06
    ierrez
    0.06
    itecture
    0.06
    Act Density 0.000%

    No Known Activations