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

    Neuronpedia

    INDEX
    Explanations

    php

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hurting
    -0.07
    蘖
    -0.07
     마련
    -0.07
    upper
    -0.07
    may
    -0.07
    啵
    -0.06
    .minute
    -0.06
     carry
    -0.06
     divides
    -0.06
    汹
    -0.06
    POSITIVE LOGITS
     safari
    0.08
    udget
    0.07
    _shuffle
    0.07
     duties
    0.07
     routine
    0.06
    岗
    0.06
     modal
    0.06
    очных
    0.06
    ский
    0.06
    Preferences
    0.06
    Act Density 0.001%

    No Known Activations