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

    Neuronpedia

    INDEX
    Explanations

    fractions of one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    """
    0.78
    Seb
    0.69
    Acute
    0.67
     except
    0.65
     Acute
    0.63
    ']
    0.63
    NOTE
    0.62
    Clark
    0.62
    except
    0.62
     Fiber
    0.61
    POSITIVE LOGITS
    nsk
    0.87
    𝗸
    0.84
     производ
    0.81
     încă
    0.80
     gewüns
    0.80
     consultas
    0.79
    ாடி
    0.79
     recomendado
    0.79
     acompañado
    0.78
     elusive
    0.78
    Act Density 0.016%

    No Known Activations