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

    Neuronpedia

    INDEX
    Explanations

    UINT

    np_max-act · gemini-2.0-flash

    The neuron does not activate on any of these code tokens—it effectively finds nothing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ANN
    -0.07
     Hyderabad
    -0.06
    VA
    -0.06
     senha
    -0.06
    YD
    -0.06
     Mev
    -0.06
     merger
    -0.06
    arkin
    -0.06
    -media
    -0.06
    _CHAN
    -0.06
    POSITIVE LOGITS
     scipy
    0.07
     Pretty
    0.07
    Plug
    0.07
     здійснення
    0.07
    float
    0.06
    photo
    0.06
     stabilization
    0.06
     sailing
    0.06
    (logging
    0.06
     stared
    0.06
    Act Density 0.012%

    No Known Activations