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

    Neuronpedia

    INDEX
    Explanations

    bubble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    钢
    -0.07
     reached
    -0.07
    RIGHT
    -0.06
     Neutral
    -0.06
    nio
    -0.06
     단
    -0.06
    �
    -0.06
    67
    -0.06
     UNICODE
    -0.06
    Weight
    -0.06
    POSITIVE LOGITS
    alking
    0.07
    ooting
    0.06
     screams
    0.06
     Sob
    0.06
    piring
    0.06
    .Fixed
    0.06
     sped
    0.06
     Εκ
    0.06
     Choir
    0.06
    _IList
    0.06
    Act Density 0.006%

    No Known Activations