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

    Neuronpedia

    INDEX
    Explanations

    bam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    am
    -0.76
    AM
    -0.69
    b
    -0.65
    word
    -0.62
    bam
    -0.61
    in
    -0.61
    p
    -0.60
    bit
    -0.58
    c
    -0.57
    i
    -0.57
    POSITIVE LOGITS
     Anſ
    1.04
     Majefty
    0.99
     Houſe
    0.93
    ſelves
    0.93
     houſe
    0.90
     myſelf
    0.90
     Reſ
    0.90
     leaſt
    0.89
     Theſe
    0.89
     faſt
    0.88
    Act Density 0.099%

    No Known Activations