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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	curr
    -0.06
    _constants
    -0.06
     gaat
    -0.06
     कभ
    -0.06
     managers
    -0.06
     channel
    -0.06
     predators
    -0.06
     capitalize
    -0.06
    READ
    -0.06
     ว
    -0.06
    POSITIVE LOGITS
     acceptable
    0.07
    _rom
    0.07
    ='./
    0.07
    ому
    0.06
    ایند
    0.06
     folly
    0.06
    修
    0.06
     tts
    0.06
     حق
    0.06
    亿
    0.06
    Act Density 0.034%

    No Known Activations