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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DIE
    -0.07
     IH
    -0.07
     CPC
    -0.07
    FM
    -0.06
     mano
    -0.06
     hä
    -0.06
     تأ
    -0.06
    ieten
    -0.06
     blk
    -0.06
    avo
    -0.06
    POSITIVE LOGITS
    Arc
    0.07
    .singleton
    0.07
     Incident
    0.07
    rowsable
    0.07
    皆
    0.06
    &,
    0.06
    -प
    0.06
     Summary
    0.06
    _inf
    0.06
    наслідок
    0.06
    Act Density 0.011%

    No Known Activations