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

    Neuronpedia

    INDEX
    Explanations

    language, errors, licensing, Lebanon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ि
    0.76
     diminish
    0.66
    ঠিক
    0.64
    الن
    0.62
     it
    0.61
     It
    0.60
    য়োজন
    0.60
    omed
    0.59
     foster
    0.59
     vapors
    0.59
    POSITIVE LOGITS
    ra
    0.92
    FBSDK
    0.82
    ☢
    0.82
     quelquefois
    0.81
    rif
    0.80
    rö
    0.79
    Ϥ
    0.79
    ptious
    0.78
    ल
    0.77
    corruption
    0.76
    Act Density 0.002%

    No Known Activations