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

    Neuronpedia

    INDEX
    Explanations

    progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ts
    -0.06
    .toList
    -0.06
    ｒ
    -0.06
     страниц
    -0.06
    _segments
    -0.06
     be
    -0.06
    :true
    -0.06
    Destroy
    -0.06
     к
    -0.05
     Raymond
    -0.05
    POSITIVE LOGITS
     synthesized
    0.07
     updating
    0.06
    .visualization
    0.06
    緊
    0.06
     브
    0.06
     Elections
    0.06
    .listen
    0.06
     refurb
    0.06
    �
    0.06
    ords
    0.06
    Act Density 0.127%

    No Known Activations