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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetSize
    -0.09
     أكد
    -0.07
     전체
    -0.07
    (&:
    -0.07
    早点
    -0.07
    _chk
    -0.07
    傩
    -0.07
    赍
    -0.07
    בצע
    -0.07
    פאר
    -0.07
    POSITIVE LOGITS
    fixed
    0.07
     strongest
    0.07
     contamin
    0.07
    -most
    0.07
    /cupertino
    0.06
     fixed
    0.06
     Tunis
    0.06
    物业管理
    0.06
     splitting
    0.06
     invariant
    0.06
    Act Density 0.007%

    No Known Activations