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

    Neuronpedia

    INDEX
    Explanations

    I'm Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mip
    0.45
     삼
    0.38
     Pem
    0.37
     बला
    0.36
    Tam
    0.35
     Ire
    0.35
    Operational
    0.35
     tam
    0.35
     Bonner
    0.35
    榜
    0.35
    POSITIVE LOGITS
    abbas
    0.38
    enger
    0.37
    ollis
    0.37
    cun
    0.35
    cous
    0.34
    ப்ஸ்
    0.34
    Joyce
    0.34
    arg
    0.33
     дополнительные
    0.33
    sliced
    0.33
    Act Density 0.010%

    No Known Activations