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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erie
    -0.07
     Beth
    -0.07
     Wilson
    -0.07
     Hal
    -0.06
     Sche
    -0.06
    erved
    -0.06
    606
    -0.06
    Tek
    -0.06
     abund
    -0.06
     switches
    -0.06
    POSITIVE LOGITS
     forget
    0.07
     wrongly
    0.07
    另一
    0.06
    �
    0.06
    :checked
    0.06
    ussy
    0.06
    -has
    0.06
    _trampoline
    0.06
    ник
    0.06
    Cannot
    0.06
    Act Density 0.002%

    No Known Activations