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

    Neuronpedia

    INDEX
    Explanations

    Defining words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Last
    -0.07
     measurable
    -0.07
    Ingredient
    -0.06
    Regular
    -0.06
     Ens
    -0.06
    ersen
    -0.06
    dap
    -0.06
     medications
    -0.06
    喜欢
    -0.06
     Cities
    -0.06
    POSITIVE LOGITS
    EventData
    0.07
    _WORDS
    0.06
    /pi
    0.06
     گوشی
    0.06
     كس
    0.06
     cooling
    0.06
    BOOLE
    0.06
    floating
    0.06
     billion
    0.06
    .pointer
    0.06
    Act Density 0.111%

    No Known Activations