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

    Neuronpedia

    INDEX
    Explanations

    Ransom payments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SAMPLE
    -0.09
     pioneering
    -0.08
     ferramenta
    -0.08
     herramienta
    -0.08
     Cars
    -0.07
     cars
    -0.07
     sail
    -0.07
     privée
    -0.07
     derivative
    -0.07
     زد
    -0.07
    POSITIVE LOGITS
     discounted
    0.09
    akc
    0.09
    aciones
    0.09
     desperation
    0.09
    Retry
    0.09
     relent
    0.08
     forgiveness
    0.08
    _retry
    0.08
     conceded
    0.08
    _restore
    0.08
    Act Density 0.056%

    No Known Activations