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

    Neuronpedia

    INDEX
    Explanations

    Recommendations or evaluations

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    ifiable
    -0.08
    天津市
    -0.07
     bipolar
    -0.07
     QUEST
    -0.07
     ie
    -0.07
    endant
    -0.07
    _isr
    -0.07
    _due
    -0.07
     כאילו
    -0.07
    ENDOR
    -0.07
    POSITIVE LOGITS
     UINavigationController
    0.07
    مرا
    0.07
    �
    0.06
    𝑉
    0.06
    谦
    0.06
    MatrixMode
    0.06
    роб
    0.06
    。“
    0.06
     Fah
    0.06
    🚦
    0.06
    Act Density 0.229%

    No Known Activations