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

    Neuronpedia

    INDEX
    Explanations

    decreasing, tailoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     रस
    -0.07
     zaz
    -0.07
     releasing
    -0.06
     ++↵
    -0.06
     /\
    -0.06
     �
    -0.06
     unlucky
    -0.06
     miraculous
    -0.06
     пу
    -0.06
    urga
    -0.06
    POSITIVE LOGITS
     Gibraltar
    0.07
    estone
    0.07
    owell
    0.07
     letech
    0.06
    ं
    0.06
     nib
    0.06
     comma
    0.06
    áků
    0.06
    /mp
    0.06
     тех
    0.06
    Act Density 0.044%

    No Known Activations