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

    Neuronpedia

    INDEX
    Explanations

    relocation/moving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entered
    -0.07
     Senator
    -0.07
     Bullet
    -0.06
    SURE
    -0.06
     swings
    -0.06
     Law
    -0.06
     creek
    -0.06
    -Benz
    -0.06
    inders
    -0.06
    Guardar
    -0.06
    POSITIVE LOGITS
    idence
    0.07
     juni
    0.06
    δος
    0.06
    monds
    0.06
    CommandEvent
    0.06
     =="
    0.06
    edení
    0.06
     şans
    0.06
     찬
    0.06
    pmat
    0.06
    Act Density 0.087%

    No Known Activations