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

    Neuronpedia

    INDEX
    Explanations

    Keyboard controls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Victim
    -0.09
     Health
    -0.07
    OUCH
    -0.07
    .Graphics
    -0.07
     Biol
    -0.07
     תיק
    -0.07
     Child
    -0.07
    /gin
    -0.07
    .exit
    -0.07
    <Button
    -0.07
    POSITIVE LOGITS
    tower
    0.08
    Period
    0.07
    -testid
    0.07
    sında
    0.07
    rece
    0.07
    routes
    0.06
     sat
    0.06
    ➥
    0.06
    ꦫ
    0.06
    metic
    0.06
    Act Density 0.035%

    No Known Activations