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

    Neuronpedia

    INDEX
    Explanations

    sniff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    33
    -0.07
     supervision
    -0.07
     earned
    -0.07
    47
    -0.07
    γού
    -0.06
    组织
    -0.06
    ΙΑΣ
    -0.06
    ักษณะ
    -0.06
     людина
    -0.06
     lent
    -0.06
    POSITIVE LOGITS
     sniff
    0.15
    .TextUtils
    0.07
     WebSocket
    0.06
     infinitely
    0.06
     ANSI
    0.06
     significantly
    0.06
     inning
    0.06
    _FAR
    0.06
     Mom
    0.06
     whistleblower
    0.06
    Act Density 0.002%

    No Known Activations