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

    Neuronpedia

    INDEX
    Explanations

    Crossing a threshold or balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encompasses
    -0.07
     باعث
    -0.07
    Concept
    -0.07
     přičemž
    -0.07
    _Login
    -0.07
    -force
    -0.06
     hizo
    -0.06
    _author
    -0.06
    yps
    -0.06
    getitem
    -0.06
    POSITIVE LOGITS
     skim
    0.08
    tah
    0.08
    amins
    0.07
    .XtraEditors
    0.07
    IAN
    0.07
    ERRY
    0.06
     Soup
    0.06
    .currency
    0.06
     Benny
    0.06
    abs
    0.06
    Act Density 0.001%

    No Known Activations