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

    Neuronpedia

    INDEX
    Explanations

    android versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Developer
    0.47
    開発
    0.45
    ・・・・
    0.44
     개발
    0.41
    developers
    0.41
    Rom
    0.41
    Minimum
    0.41
     Developer
    0.40
    ீஸ்
    0.40
    反馈
    0.40
    POSITIVE LOGITS
     Durant
    0.38
     approached
    0.35
     shrank
    0.34
     cow
    0.34
     sl
    0.34
    wf
    0.34
     occupants
    0.33
     Kru
    0.33
     bowed
    0.33
    ivre
    0.33
    Act Density 0.000%

    No Known Activations