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

    Neuronpedia

    INDEX
    Explanations

    recommendations, usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mono
    -0.07
     Lam
    -0.07
     hadde
    -0.07
    aporan
    -0.07
     Mai
    -0.06
    Disclosure
    -0.06
    _use
    -0.06
    افه
    -0.06
    _hop
    -0.06
     interpolate
    -0.06
    POSITIVE LOGITS
    ields
    0.07
    NOW
    0.06
    rew
    0.06
     коман
    0.06
    CREASE
    0.06
    br
    0.06
    �名
    0.06
    حی
    0.06
    QT
    0.06
    面積
    0.06
    Act Density 0.051%

    No Known Activations