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

    Neuronpedia

    INDEX
    Explanations

    preceding the word key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hires
    0.84
    滙
    0.79
     Notebook
    0.79
     threats
    0.78
    礡
    0.78
     уви
    0.77
     modifications
    0.77
     Configuring
    0.76
     ワイド
    0.75
     configurations
    0.75
    POSITIVE LOGITS
    mu
    0.80
    CharField
    0.75
    nhold
    0.73
    sd
    0.72
    Joseph
    0.71
    nett
    0.70
    Alc
    0.69
    did
    0.68
    slope
    0.68
    ness
    0.68
    Act Density 0.072%

    No Known Activations