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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    Explanation: All activations are zero, so this neuron is effectively “dead” and does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VertexUvs
    -0.07
     hatır
    -0.07
     CircularProgress
    -0.07
    vr
    -0.07
     kanıt
    -0.06
     Git
    -0.06
     наук
    -0.06
     eskorte
    -0.06
    _heat
    -0.06
    abytes
    -0.06
    POSITIVE LOGITS
    0
    0.08
    Listen
    0.07
     SE
    0.07
    CodeGen
    0.07
     La
    0.06
    вание
    0.06
    -quote
    0.06
     confined
    0.06
    st
    0.06
     Playing
    0.06
    Act Density 0.009%

    No Known Activations