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

    Neuronpedia

    INDEX
    Explanations

    instructions and troubleshooting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _append
    -0.07
    /font
    -0.06
    ような
    -0.06
    aqu
    -0.06
    عاد
    -0.06
    ernals
    -0.06
     appeals
    -0.06
    цу
    -0.06
     کش
    -0.06
    CS
    -0.06
    POSITIVE LOGITS
     (*.
    0.07
     Stellar
    0.07
     Astro
    0.07
    Facing
    0.07
    _ELEM
    0.06
     empathy
    0.06
     ):↵↵
    0.06
     assort
    0.06
    ([$
    0.06
     Alfred
    0.06
    Act Density 0.024%

    No Known Activations