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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羅
    -0.07
    _ul
    -0.06
     tex
    -0.06
    _compat
    -0.06
    ظيف
    -0.06
     differentiation
    -0.06
     validators
    -0.06
     monkeys
    -0.06
    áč
    -0.06
    ascular
    -0.06
    POSITIVE LOGITS
    στή
    0.07
     heartfelt
    0.07
    	spin
    0.07
    Hover
    0.06
    zx
    0.06
     kısm
    0.06
    [user
    0.06
     grips
    0.06
    bye
    0.06
    _process
    0.06
    Act Density 0.012%

    No Known Activations