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

    Neuronpedia

    INDEX
    Explanations

    line-by-line coding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    angled
    0.55
     മത്സര
    0.53
     সিংহের
    0.53
     எழுத்த
    0.52
    addressed
    0.51
    anceled
    0.50
     startled
    0.50
    ņem
    0.50
    substituted
    0.49
    ാരോഗ്യ
    0.48
    POSITIVE LOGITS
    Ş
    0.52
     debug
    0.50
    תו
    0.49
    동
    0.49
    광
    0.48
    ופי
    0.48
    תי
    0.48
    Ster
    0.46
    인지
    0.46
    に伴
    0.46
    Act Density 0.002%

    No Known Activations