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

    Neuronpedia

    INDEX
    Explanations

    varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staveb
    -0.07
    _Private
    -0.06
    [NUM
    -0.06
     syslog
    -0.06
    kok
    -0.06
     {}),↵
    -0.06
    _setopt
    -0.06
     demeanor
    -0.06
     remake
    -0.06
     hashed
    -0.06
    POSITIVE LOGITS
    auc
    0.07
     exploiting
    0.07
     exploited
    0.07
    ElapsedTime
    0.06
    months
    0.06
    May
    0.06
    _PK
    0.06
     guarantee
    0.06
     må
    0.06
    Sensitive
    0.06
    Act Density 0.000%

    No Known Activations