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

    Neuronpedia

    INDEX
    Explanations

    names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۱۵
    0.50
     unambiguously
    0.50
    に取り組
    0.50
     contamin
    0.48
     monolith
    0.47
     ambayo
    0.47
     चुना
    0.47
     загряз
    0.47
     nível
    0.46
    こだわ
    0.46
    POSITIVE LOGITS
    at
    0.45
     Barry
    0.44
    ur
    0.43
    Barry
    0.43
    ír
    0.43
     Robert
    0.42
    Ernest
    0.42
    Derek
    0.41
     Roger
    0.40
    Robert
    0.39
    Act Density 0.000%

    No Known Activations