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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intens
    -0.07
    움
    -0.06
     murdering
    -0.06
     breaks
    -0.06
     outras
    -0.06
    ning
    -0.06
    ीदव
    -0.06
     functioning
    -0.06
     чувств
    -0.06
    수의
    -0.06
    POSITIVE LOGITS
    ultimate
    0.07
     Ahead
    0.06
    Manual
    0.06
    Washington
    0.06
    cached
    0.06
    TargetException
    0.06
    AtIndex
    0.06
     Malik
    0.06
     ahead
    0.06
    tbl
    0.05
    Act Density 0.006%

    No Known Activations