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

    Neuronpedia

    INDEX
    Explanations

    par

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }}">{{$
    -0.07
    _green
    -0.07
    .alpha
    -0.06
    اون
    -0.06
    Esp
    -0.06
    -light
    -0.06
    俗
    -0.06
    	names
    -0.06
    ัพย
    -0.06
    -0.06
    POSITIVE LOGITS
     информ
    0.07
     milyon
    0.07
    All
    0.07
     tragedies
    0.06
     Vampire
    0.06
    .what
    0.06
    acimiento
    0.06
     insulin
    0.06
    AMAGE
    0.06
     fishermen
    0.06
    Act Density 0.003%

    No Known Activations