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

    Neuronpedia

    INDEX
    Explanations

    enumerated lists and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offerings
    0.54
    .
    0.52
     outlets
    0.51
     for
    0.50
     👀
    0.48
     suitors
    0.48
     dosages
    0.47
     summaries
    0.46
     admirers
    0.46
     by
    0.45
    POSITIVE LOGITS
    c
    0.79
    n
    0.74
    k
    0.73
    kita
    0.65
    b
    0.62
    safety
    0.61
    f
    0.60
    g
    0.59
    m
    0.58
     ordine
    0.56
    Act Density 0.184%

    No Known Activations