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

    Neuronpedia

    INDEX
    Explanations

    (k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touted
    -0.07
     сель
    -0.06
    losing
    -0.06
    /png
    -0.06
     Glass
    -0.06
    perience
    -0.06
    chester
    -0.06
    cccc
    -0.05
    bon
    -0.05
     MILL
    -0.05
    POSITIVE LOGITS
    _SEGMENT
    0.08
     �
    0.07
    (scale
    0.07
    (generator
    0.07
     Toe
    0.07
     Şimdi
    0.06
    .Update
    0.06
     kh
    0.06
    >Z
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations