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

    Neuronpedia

    INDEX
    Explanations

    defining concepts/terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.48
     juga
    0.42
    한테
    0.40
    ข
    0.39
    YYYY
    0.39
    """
    0.38
     auch
    0.38
     Mail
    0.37
    ถือ
    0.37
    ["
    0.37
    POSITIVE LOGITS
     scienze
    0.52
    हालय
    0.49
     actitudes
    0.46
    atletas
    0.45
     réactions
    0.44
     prezident
    0.44
     organizações
    0.43
     irure
    0.43
     polysaccharides
    0.43
     organizaciones
    0.43
    Act Density 0.026%

    No Known Activations