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

    Neuronpedia

    INDEX
    Explanations

    Markup symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -colored
    -0.07
     sensitivity
    -0.07
    ubi
    -0.06
    _sms
    -0.06
    orange
    -0.06
     exhaustive
    -0.06
    стю
    -0.06
    otope
    -0.06
     active
    -0.06
     gritty
    -0.06
    POSITIVE LOGITS
    �
    0.06
     schö
    0.06
     sinc
    0.06
    675
    0.06
     flashed
    0.06
     �
    0.06
     dk
    0.06
    <l
    0.06
     bending
    0.05
    TouchUpInside
    0.05
    Act Density 0.044%

    No Known Activations