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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emit
    -0.08
    league
    -0.07
    StepThrough
    -0.06
     Sender
    -0.06
    sing
    -0.06
    endpoint
    -0.06
     мати
    -0.06
    iễn
    -0.06
    .detectChanges
    -0.06
    composed
    -0.06
    POSITIVE LOGITS
    getKey
    0.08
    
    0.07
    insky
    0.07
     Tob
    0.06
     tady
    0.06
     fabrication
    0.06
     who
    0.06
    エ
    0.06
     Diane
    0.06
     annihil
    0.06
    Act Density 0.109%

    No Known Activations