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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gas
    -0.06
    _rad
    -0.06
    �a
    -0.06
    Shield
    -0.06
    .mask
    -0.06
    ircon
    -0.06
     Guil
    -0.06
     trapping
    -0.06
    Hal
    -0.06
    Clip
    -0.06
    POSITIVE LOGITS
    .Execution
    0.07
     spawn
    0.07
     ＼↵
    0.06
     철
    0.06
     Persona
    0.06
     tunes
    0.06
     determin
    0.06
    uchos
    0.06
    .selection
    0.06
     painstaking
    0.06
    Act Density 0.210%

    No Known Activations