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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    翼
    -0.07
    ㉰
    -0.07
    蔈
    -0.07
     בקרב
    -0.07
    早晚
    -0.07
    龇
    -0.07
    历来
    -0.07
    可爱的
    -0.07
     Sikh
    -0.06
    .rev
    -0.06
    POSITIVE LOGITS
    呈現
    0.07
    _water
    0.07
    概括
    0.07
    -re
    0.07
     interrog
    0.06
     alternative
    0.06
    _hits
    0.06
     tt
    0.06
     Vienna
    0.06
     applicable
    0.06
    Act Density 0.003%

    No Known Activations