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

    Neuronpedia

    INDEX
    Explanations

    say "name"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    煸
    -0.07
    Compose
    -0.07
    azing
    -0.07
    枢
    -0.07
    ately
    -0.06
     preliminary
    -0.06
     cheese
    -0.06
    细胞
    -0.06
    ruise
    -0.06
     tumble
    -0.06
    POSITIVE LOGITS
    Israel
    0.07
    Contain
    0.06
     Keyboard
    0.06
     unlocks
    0.06
    KW
    0.06
     tvb
    0.06
     })(
    0.06
    >>(
    0.06
    適合
    0.06
     whisper
    0.06
    Act Density 0.036%

    No Known Activations