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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сю
    -0.06
     Ellen
    -0.06
    orex
    -0.06
    stra
    -0.06
    meer
    -0.06
    รร
    -0.06
    ný
    -0.06
     Sandwich
    -0.06
     akan
    -0.06
     vyj
    -0.06
    POSITIVE LOGITS
    Validator
    0.07
     Particularly
    0.07
     Unused
    0.07
    thanks
    0.06
     morb
    0.06
    Ο
    0.06
    Makes
    0.06
     tard
    0.06
    –
    0.06
    _verified
    0.06
    Act Density 0.000%

    No Known Activations