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

    Neuronpedia

    INDEX
    Explanations

    apology/rejection phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cors
    -0.07
     affidavit
    -0.07
     필
    -0.07
    Attachments
    -0.07
    WithTitle
    -0.07
    ใช
    -0.06
    ⧪
    -0.06
    結束
    -0.06
    \User
    -0.06
     fade
    -0.06
    POSITIVE LOGITS
    养育
    0.08
    .spring
    0.07
     Primer
    0.07
    (curr
    0.07
    _pairs
    0.07
     blowing
    0.07
     BP
    0.07
    compound
    0.07
    pp
    0.06
     pong
    0.06
    Act Density 0.006%

    No Known Activations