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

    Neuronpedia

    INDEX
    Explanations

    but followed by limitations or qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surgiu
    0.50
     தோன்ற
    0.47
     its
    0.47
     বৃত্তান্ত
    0.47
     pharmacokinetic
    0.47
     dikdört
    0.46
     imasmim
    0.46
     był
    0.46
     currants
    0.46
     llevaba
    0.45
    POSITIVE LOGITS
    くて
    0.54
    r
    0.48
    kter
    0.47
    ravi
    0.46
    ἰ
    0.45
    ningar
    0.45
    ll
    0.45
    ligare
    0.44
    ters
    0.44
    ziger
    0.43
    Act Density 0.120%

    No Known Activations