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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .charset
    -0.07
     temple
    -0.07
     portraying
    -0.07
     Alf
    -0.07
    .TextField
    -0.07
    𝒉
    -0.07
     USERNAME
    -0.07
    טייל
    -0.07
    _gettime
    -0.06
     Victory
    -0.06
    POSITIVE LOGITS
    共产党员
    0.08
     sav
    0.07
     куд
    0.07
     Status
    0.07
    -links
    0.06
    계획
    0.06
     non
    0.06
    )+
    0.06
    odings
    0.06
     Chair
    0.06
    Act Density 0.012%

    No Known Activations