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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anonymously
    -0.09
     htmlspecialchars
    -0.08
     urls
    -0.08
     neighborhoods
    -0.07
    .They
    -0.07
     Annunci
    -0.07
    YPES
    -0.07
    佾
    -0.07
    --[
    -0.07
    ,this
    -0.07
    POSITIVE LOGITS
    ................
    0.07
    omentum
    0.07
     whats
    0.07
     arrayWith
    0.07
    ➽
    0.06
    ────────
    0.06
    关键是
    0.06
     "{"
    0.06
    creates
    0.06
    gett
    0.06
    Act Density 0.236%

    No Known Activations