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

    Neuronpedia

    INDEX
    Explanations

    CSS gradients

    np_max-act · gemini-2.0-flash

    The neuron never activates on any input (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    909
    -0.07
    rij
    -0.06
     kah
    -0.06
     Ident
    -0.06
     vazgeç
    -0.06
     uprav
    -0.06
     Jain
    -0.06
     شده
    -0.06
     Coastal
    -0.06
     emphas
    -0.06
    POSITIVE LOGITS
     ###↵
    0.06
    leftright
    0.06
    liğ
    0.06
     Sirius
    0.06
    -house
    0.06
    ケット
    0.06
    "?↵↵
    0.06
     issuance
    0.06
     menstrual
    0.06
    ünüz
    0.06
    Act Density 0.001%

    No Known Activations