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

    Neuronpedia

    INDEX
    Explanations

    changes, endings, turning points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (assign
    -0.07
     Haley
    -0.07
    LTR
    -0.07
     queued
    -0.07
    ']},↵
    -0.06
    لد
    -0.06
    _Matrix
    -0.06
    .getView
    -0.06
     @}
    -0.06
     lá
    -0.06
    POSITIVE LOGITS
    쓩
    0.08
    itbart
    0.07
    xEF
    0.07
     khoản
    0.07
    蛱
    0.07
    琤
    0.07
    �
    0.07
    iner
    0.06
     showError
    0.06
    校园
    0.06
    Act Density 0.128%

    No Known Activations