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

    Neuronpedia

    INDEX
    Explanations

    structured definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其
    0.45
    ”).
    0.44
     बिता
    0.42
     its
    0.38
    天的
    0.38
    )).
    0.38
    然而
    0.38
    ®.
    0.38
     sources
    0.38
     tikai
    0.38
    POSITIVE LOGITS
     Те
    0.35
    uola
    0.35
    icture
    0.34
     Со
    0.34
    berts
    0.34
    ்
    0.33
    zus
    0.33
    ate
    0.32
    rawberry
    0.32
     ஒழு
    0.32
    Act Density 0.084%

    No Known Activations