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

    Neuronpedia

    INDEX
    Explanations

    reflex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('');↵↵
    -0.07
    .com
    -0.06
     dirt
    -0.06
    ('');↵
    -0.06
    _Var
    -0.06
     intimid
    -0.06
     sanit
    -0.06
    кав
    -0.06
     bomb
    -0.06
    インタ
    -0.06
    POSITIVE LOGITS
     reflex
    0.18
     Reflex
    0.15
     reflexivity
    0.10
     httpResponse
    0.08
    lex
    0.07
    flex
    0.07
    ileged
    0.07
     Regex
    0.07
    _mex
    0.07
    ension
    0.07
    Act Density 0.002%

    No Known Activations