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

    Neuronpedia

    INDEX
    Explanations

    other, any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mocking
    -0.08
    Zen
    -0.06
    ,tmp
    -0.06
     tonic
    -0.06
     apartment
    -0.06
    Chip
    -0.06
     tears
    -0.06
     breakfast
    -0.06
    [],
    -0.06
     Ful
    -0.06
    POSITIVE LOGITS
    ++){↵↵
    0.08
     ücretsiz
    0.07
    __':
↵
    0.06
     پن
    0.06
    estureRecognizer
    0.06
    emetery
    0.06
     أحد
    0.06
     hissed
    0.06
    食品
    0.06
    (stderr
    0.06
    Act Density 0.014%

    No Known Activations