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

    Neuronpedia

    INDEX
    Explanations

    the new, three key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    چی
    0.43
    Fl
    0.42
    Yet
    0.40
    Conservation
    0.39
    fl
    0.39
    वण्यात
    0.39
     দূত
    0.39
    OEt
    0.38
    چا
    0.38
    വദ
    0.38
    POSITIVE LOGITS
    autes
    0.38
     الترك
    0.37
     fire
    0.37
     autobiography
    0.36
     Harris
    0.34
     ألف
    0.34
    éristique
    0.34
    inna
    0.34
    oley
    0.33
     McCall
    0.33
    Act Density 0.000%

    No Known Activations