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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    google
    -0.07
    <?=
    -0.07
     جمله
    -0.06
     Air
    -0.06
     Galaxy
    -0.06
    -playing
    -0.06
     Sheets
    -0.06
    UREMENT
    -0.06
    422
    -0.06
    約
    -0.06
    POSITIVE LOGITS
     bald
    0.07
    _skills
    0.06
    　　　　　　　
    0.06
    HEIGHT
    0.06
     intoler
    0.06
    .listBox
    0.06
     exped
    0.06
    】,【
    0.06
    (dev
    0.06
    бург
    0.06
    Act Density 0.011%

    No Known Activations