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

    Neuronpedia

    INDEX
    Explanations

    Possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toolkit
    -0.07
    _changed
    -0.07
    	timeout
    -0.06
    _seen
    -0.06
    ongyang
    -0.06
    atha
    -0.06
    .bind
    -0.06
     therapies
    -0.06
     тка
    -0.06
     Providers
    -0.06
    POSITIVE LOGITS
    toFloat
    0.07
    _Order
    0.06
     stumbling
    0.06
    ida
    0.06
     usher
    0.06
    aye
    0.06
    ember
    0.06
    Для
    0.05
    Atlantic
    0.05
     experiment
    0.05
    Act Density 0.009%

    No Known Activations