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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unauthorized
    -0.07
     высокой
    -0.07
     arac
    -0.06
     Watching
    -0.06
     graded
    -0.06
     bout
    -0.06
     FormControl
    -0.06
    	ac
    -0.06
    amo
    -0.06
     te
    -0.06
    POSITIVE LOGITS
    _calls
    0.08
    ữ
    0.07
     tirelessly
    0.07
    -Time
    0.07
     Глав
    0.07
     prosecuted
    0.06
    opens
    0.06
     invest
    0.06
     Stores
    0.06
    �
    0.06
    Act Density 0.020%

    No Known Activations