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

    Neuronpedia

    INDEX
    Explanations

    root of or seeds of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DISCLAIMED
    0.89
    ᄂ
    0.86
     Bob
    0.84
    bik
    0.84
     Thy
    0.84
    劧
    0.83
    <bos>
    0.83
    ဝန်
    0.82
    ಪು
    0.80
     admirers
    0.79
    POSITIVE LOGITS
    hdad
    0.72
     disert
    0.70
     лежит
    0.70
     sprouted
    0.68
     основу
    0.68
    roots
    0.68
     লুকিয়ে
    0.67
     sommes
    0.67
    atti
    0.65
    ida
    0.65
    Act Density 0.277%

    No Known Activations