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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecause
    -0.09
    alance
    -0.08
    ubbles
    -0.08
    eyond
    -0.08
    odega
    -0.08
     Equip
    -0.07
    UILT
    -0.07
    LOOD
    -0.07
    ecome
    -0.07
    etween
    -0.07
    POSITIVE LOGITS
    B
    0.11
     Benson
    0.10
     B
    0.10
    b
    0.10
     Boris
    0.10
     b
    0.10
     BJ
    0.10
     Brett
    0.09
     B
    0.09
     BF
    0.09
    Act Density 0.720%

    No Known Activations