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

    Neuronpedia

    INDEX
    Explanations

    energy drinks and caffeine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Criterion
    -0.07
    Logging
    -0.07
    _Params
    -0.06
    Vect
    -0.06
    _filenames
    -0.06
    	options
    -0.06
     pylint
    -0.06
    .script
    -0.06
    quarter
    -0.06
    Universal
    -0.06
    POSITIVE LOGITS
     Hav
    0.07
    bare
    0.07
    dest
    0.07
    tok
    0.07
    �
    0.06
    Program
    0.06
    атом
    0.06
     Matt
    0.06
    침
    0.06
    Cost
    0.06
    Act Density 0.010%

    No Known Activations