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

    Neuronpedia

    INDEX
    Explanations

    Number 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paso
    -0.08
    спор
    -0.08
    𝜏
    -0.08
    STOP
    -0.08
    ż
    -0.07
     Joi
    -0.07
     Swal
    -0.07
    当之无
    -0.07
    rror
    -0.07
    🥊
    -0.07
    POSITIVE LOGITS
    angling
    0.07
    comput
    0.07
    "
↵
    0.07
    année
    0.07
     cancelled
    0.07
    蓝
    0.07
    inating
    0.07
    _cur
    0.07
    년
    0.06
     cur
    0.06
    Act Density 0.038%

    No Known Activations