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

    Neuronpedia

    INDEX
    Explanations

    surviving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birinin
    -0.07
    夢
    -0.07
     海
    -0.07
     rés
    -0.06
    assertTrue
    -0.06
    773
    -0.06
    iclass
    -0.06
    ladatel
    -0.06
    _SERVER
    -0.06
    jj
    -0.05
    POSITIVE LOGITS
    Array
    0.06
    aways
    0.06
    )

↵
    0.06
    .WARNING
    0.06
     privat
    0.06
     ко
    0.06
    ssl
    0.06
     "$(
    0.06
     persec
    0.06
    /Q
    0.06
    Act Density 0.117%

    No Known Activations