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

    Neuronpedia

    INDEX
    Explanations

    base number conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vasion
    -0.07
    อำ
    -0.07
     ICE
    -0.07
    _STORAGE
    -0.07
    .bundle
    -0.07
     unrecognized
    -0.07
    =pos
    -0.07
    怩
    -0.07
     Firebase
    -0.07
    .args
    -0.06
    POSITIVE LOGITS
    厨
    0.08
    _J
    0.07
    廚
    0.07
    上司
    0.07
    עלי
    0.07
    טקסט
    0.07
    0.06
    (text
    0.06
    ('"
    0.06
    十字
    0.06
    Act Density 0.008%

    No Known Activations