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

    Neuronpedia

    INDEX
    Explanations

    grid position indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bluish
    0.86
    ｰ
    0.85
     flares
    0.84
    olip
    0.81
     condiments
    0.80
    aros
    0.79
     immunohist
    0.77
     পন্থা
    0.77
    ématiques
    0.77
    °,
    0.77
    POSITIVE LOGITS
     Lodge
    0.67
    相互
    0.67
     Jeden
    0.66
    क्साइड
    0.65
     Jako
    0.64
     Kingdom
    0.62
    గే
    0.61
     gewisse
    0.60
    彼此
    0.60
     jeden
    0.60
    Act Density 0.144%

    No Known Activations