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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any token and thus does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ISTS
    -0.07
    ART
    -0.06
    ート
    -0.06
    GLE
    -0.06
    Fire
    -0.06
    115
    -0.06
    that
    -0.06
     achievements
    -0.06
     Dropbox
    -0.06
    ioneer
    -0.06
    POSITIVE LOGITS
    ＿__
    0.07
    uyệt
    0.07
    .geo
    0.06
     posterior
    0.06
    buat
    0.06
    θεση
    0.06
    　j
    0.06
     proportion
    0.06
     lor
    0.06
     equivalence
    0.06
    Act Density 0.031%

    No Known Activations