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

    Neuronpedia

    INDEX
    Explanations

    Knowledge and awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    舉
    -0.07
    rw
    -0.06
    ために
    -0.06
     NPC
    -0.06
    nim
    -0.06
     rozší
    -0.06
     Chiến
    -0.06
     Clair
    -0.06
    .Accept
    -0.06
    Winvalid
    -0.06
    POSITIVE LOGITS
    ESTAMP
    0.07
     doubt
    0.07
     essere
    0.07
     therm
    0.07
    거리
    0.06
     t
    0.06
     individually
    0.06
    wjgl
    0.06
     t
    0.06
    -password
    0.06
    Act Density 0.000%

    No Known Activations