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

    Neuronpedia

    INDEX
    Explanations

    code/math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .leave
    -0.07
    кав
    -0.07
    .float
    -0.06
    _portal
    -0.06
     opened
    -0.06
     Wimbledon
    -0.06
     hookers
    -0.06
     dosud
    -0.06
     Bahamas
    -0.06
     fiction
    -0.06
    POSITIVE LOGITS
     Maver
    0.07
     horrors
    0.06
    _PART
    0.06
    ät
    0.06
    豊
    0.06
    äre
    0.06
    erd
    0.06
     VIR
    0.06
    reich
    0.06
    _COMPLETE
    0.06
    Act Density 0.009%

    No Known Activations