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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Skip
    -0.07
    _cliente
    -0.07
    .Send
    -0.07
    Processor
    -0.07
    <Select
    -0.07
     reefs
    -0.06
    ('?
    -0.06
     Grow
    -0.06
     deceive
    -0.06
    得了
    -0.06
    POSITIVE LOGITS
    坚固
    0.07
    �
    0.07
    straint
    0.07
    врем
    0.07
    middle
    0.06
    .design
    0.06
    AY
    0.06
     только
    0.06
    //--------------------------------
    0.06
    ساس
    0.06
    Act Density 0.015%

    No Known Activations