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

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combina
    -0.08
     ↵↵↵↵
    -0.08
     комбина
    -0.08
     Bruins
    -0.07
     lawsuits
    -0.07
     nello
    -0.07
     شک
    -0.07
     juridische
    -0.07
     combination
    -0.07
    ayed
    -0.07
    POSITIVE LOGITS
    Reserve
    0.08
     Reserve
    0.08
    pox
    0.08
    ків
    0.08
    kip
    0.08
    idue
    0.08
    пон
    0.07
    ponsor
    0.07
     réserv
    0.07
     réservé
    0.07
    Act Density 0.000%

    No Known Activations