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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FRAME
    -0.07
    𬳵
    -0.07
    <bool
    -0.07
     model
    -0.07
     we
    -0.07
    	controller
    -0.07
    .bus
    -0.06
    끼
    -0.06
    /block
    -0.06
    Validate
    -0.06
    POSITIVE LOGITS
    альных
    0.07
    كهرب
    0.07
     Nina
    0.07
    庶
    0.07
     Atat
    0.06
    此外
    0.06
    漉
    0.06
     Carly
    0.06
    évén
    0.06
    مواق
    0.06
    Act Density 0.003%

    No Known Activations