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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yii
    -0.07
    ጅ
    -0.07
     agr
    -0.07
     grands
    -0.07
    ⚁
    -0.07
    .View
    -0.07
    자동차
    -0.07
     MATRIX
    -0.07
     Highland
    -0.06
     Lind
    -0.06
    POSITIVE LOGITS
    _needed
    0.07
     OT
    0.07
     ripped
    0.07
    olv
    0.07
    oven
    0.06
    あなた
    0.06
     dialogue
    0.06
    光芒
    0.06
    lat
    0.06
     ripping
    0.06
    Act Density 0.027%

    No Known Activations