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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    --------------------------------------------------------------------------↵
    -0.08
     دوباره
    -0.07
    ではない
    -0.07
     acceptance
    -0.07
    罚
    -0.07
     pessoas
    -0.06
     зд
    -0.06
    -0.06
     ام
    -0.06
     crib
    -0.06
    POSITIVE LOGITS
    concept
    0.06
     radiant
    0.06
     toxic
    0.06
    erg
    0.06
    zet
    0.06
    	BIT
    0.06
    (ph
    0.06
     thật
    0.06
     firewall
    0.06
     seamlessly
    0.06
    Act Density 0.000%

    No Known Activations