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

    Neuronpedia

    INDEX
    Explanations

    told

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employees
    -0.07
    気になる
    -0.07
    Freq
    -0.07
    \Url
    -0.07
    טון
    -0.07
    上がる
    -0.06
    Mutex
    -0.06
     Ex
    -0.06
    @register
    -0.06
    /bootstrap
    -0.06
    POSITIVE LOGITS
    alen
    0.07
    ﲋ
    0.07
    adden
    0.07
    opathy
    0.07
    Wind
    0.07
     כמה
    0.07
    .published
    0.06
    Volume
    0.06
    ()-
    0.06
    ᾰ
    0.06
    Act Density 0.018%

    No Known Activations