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

    Neuronpedia

    INDEX
    Explanations

    Action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forwards
    -0.07
    아서
    -0.07
    oubles
    -0.07
    uyen
    -0.06
     plaint
    -0.06
    rams
    -0.06
     anyhow
    -0.06
     přib
    -0.06
    achte
    -0.06
     hizmet
    -0.06
    POSITIVE LOGITS
    (figsize
    0.07
    Directories
    0.07
    .pkg
    0.07
     Locale
    0.07
    _coll
    0.07
     FileManager
    0.06
     IDM
    0.06
     Ill
    0.06
    -sizing
    0.06
     Criterion
    0.06
    Act Density 0.000%

    No Known Activations