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

    Neuronpedia

    INDEX
    Explanations

    browse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blown
    -1.08
     blow
    -1.02
    blow
    -1.02
     blowing
    -1.00
     blew
    -0.95
     Blow
    -0.90
    blown
    -0.86
     nakalista
    -0.83
    blowing
    -0.81
    Blow
    -0.79
    POSITIVE LOGITS
     CanadaChoose
    0.47
    links
    0.46
     سكان
    0.46
    Links
    0.44
     cref
    0.43
    reciate
    0.42
     by
    0.41
     kwe
    0.41
     into
    0.41
    ings
    0.40
    Act Density 0.130%

    No Known Activations