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

    Neuronpedia

    INDEX
    Explanations

    lightly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inth
    -0.08
     correctly
    -0.08
    UITable
    -0.08
    alsex
    -0.08
    orgeous
    -0.07
     concord
    -0.07
     seamlessly
    -0.07
     öt
    -0.07
    ology
    -0.07
     richly
    -0.07
    POSITIVE LOGITS
     shrimp
    0.08
    �
    0.08
    程度
    0.08
     hairs
    0.07
    ासा
    0.07
     desperation
    0.07
    イブ
    0.07
     ημέ
    0.07
     преподав
    0.07
     utilizes
    0.07
    Act Density 0.005%

    No Known Activations