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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Table
    -0.07
    .AR
    -0.07
    lem
    -0.06
    げ
    -0.06
     الو
    -0.06
    PROTO
    -0.06
    fff
    -0.06
    �
    -0.06
    _lines
    -0.06
    ्पन
    -0.06
    POSITIVE LOGITS
     achieve
    0.07
    且
    0.06
    usion
    0.06
     oben
    0.06
     sống
    0.06
     userProfile
    0.06
     Breed
    0.06
    に入
    0.06
    legt
    0.06
     Sed
    0.06
    Act Density 0.008%

    No Known Activations