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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead—it never activates on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .gf
    -0.06
     intersects
    -0.06
    ceans
    -0.06
     ин
    -0.06
     outputStream
    -0.06
     Movement
    -0.06
     rift
    -0.06
     ler
    -0.06
    .l
    -0.06
    .Marker
    -0.06
    POSITIVE LOGITS
    acerb
    0.06
     nevid
    0.06
    _stderr
    0.06
    筆
    0.06
     gratis
    0.06
     좋아
    0.06
     Ange
    0.06
    Owned
    0.06
     Toy
    0.06
    {{--
    0.06
    Act Density 0.007%

    No Known Activations