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

    Neuronpedia

    INDEX
    Explanations

    negative outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     несколько
    -0.07
    -sensitive
    -0.07
    爆
    -0.07
    .gradient
    -0.07
     barn
    -0.07
     youtube
    -0.07
    endar
    -0.07
     ум
    -0.06
     maternity
    -0.06
     knowing
    -0.06
    POSITIVE LOGITS
    assist
    0.06
    iele
    0.06
    raise
    0.06
    nbsp
    0.06
    max
    0.06
     реак
    0.06
    Reaction
    0.06
    Color
    0.06
    onation
    0.06
     συνο
    0.06
    Act Density 0.024%

    No Known Activations