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

    Neuronpedia

    INDEX
    Explanations

    CI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aupt
    -0.07
     �
    -0.07
    드
    -0.07
    먹
    -0.07
     Suk
    -0.07
    jec
    -0.07
    _updated
    -0.07
    ыш
    -0.07
    现金
    -0.07
     tart
    -0.07
    POSITIVE LOGITS
     planting
    0.07
    ちは
    0.07
     الرو
    0.07
     FI
    0.07
    굛
    0.07
    urchases
    0.07
     Suicide
    0.06
     Shooting
    0.06
     acupuncture
    0.06
    ility
    0.06
    Act Density 0.000%

    No Known Activations