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

    Neuronpedia

    INDEX
    Explanations

    user input in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accounts
    -0.07
     olma
    -0.06
     сид
    -0.06
    _DAC
    -0.06
     localized
    -0.06
    shirt
    -0.06
     blk
    -0.06
    astered
    -0.06
    HEY
    -0.06
    zilla
    -0.06
    POSITIVE LOGITS
    ilit
    0.06
    (prev
    0.06
     reaction
    0.06
    ifs
    0.06
    aji
    0.06
    awe
    0.06
    Allow
    0.06
     Lor
    0.06
    «
    0.06
     bloss
    0.06
    Act Density 0.030%

    No Known Activations