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

    Neuronpedia

    INDEX
    Explanations

    end of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enschap
    0.37
    )、
    0.35
     사람
    0.35
     ئى
    0.35
    」「
    0.34
     Saltar
    0.34
     yuan
    0.33
     shaman
    0.33
    했고
    0.32
     autobus
    0.32
    POSITIVE LOGITS
    ↵↵↵↵
    1.31
    ↵↵↵
    1.28
    ↵↵↵↵↵
    1.25
    ↵↵↵↵↵↵↵↵↵↵↵
    1.08
    ↵↵↵↵↵↵↵
    1.06
    ↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
    ↵↵↵↵↵↵↵↵
    1.00
    ↵↵↵↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.99
    Act Density 0.128%

    No Known Activations