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

    Neuronpedia

    INDEX
    Explanations

    shimmers in the light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    innen
    0.89
    ron
    0.83
    ines
    0.82
    icks
    0.81
    ily
    0.81
    lo
    0.80
    rm
    0.79
    angan
    0.77
    issant
    0.77
    negara
    0.76
    POSITIVE LOGITS
    ἲ
    0.96
     الز
    0.83
    0.81
    贝
    0.80
    F
    0.80
     λά
    0.79
    ਤਾ
    0.79
    يتر
    0.79
     difíc
    0.77
     రై
    0.77
    Act Density 0.001%

    No Known Activations