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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marital
    -0.07
    άννης
    -0.06
    mnop
    -0.06
     Senator
    -0.06
    _SHARED
    -0.06
     restau
    -0.06
     electoral
    -0.06
     civic
    -0.06
     Rocky
    -0.06
    願
    -0.06
    POSITIVE LOGITS
     affiliates
    0.07
     jue
    0.06
     €
    0.06
    فی
    0.06
    _DURATION
    0.06
    */↵
    0.06
    报
    0.06
    —
    0.06
     depicting
    0.06
     DIC
    0.06
    Act Density 0.026%

    No Known Activations