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

    Neuronpedia

    INDEX
    Explanations

    Web page excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Double
    -0.07
     shootings
    -0.07
    AV
    -0.07
     PO
    -0.06
     flashlight
    -0.06
    っぱい
    -0.06
    attached
    -0.06
    (ph
    -0.06
    夫
    -0.06
    -media
    -0.06
    POSITIVE LOGITS
     axs
    0.07
    णन
    0.07
    ализи
    0.07
    679
    0.07
     southern
    0.07
    .addTarget
    0.07
     giov
    0.06
    oq
    0.06
    -heavy
    0.06
     "\(
    0.06
    Act Density 0.050%

    No Known Activations