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

    Neuronpedia

    INDEX
    Explanations

    work on/together/breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anud
    0.81
     opt
    0.70
     parib
    0.70
     действу
    0.70
    arctan
    0.70
     prise
    0.69
    เล่น
    0.69
    wide
    0.68
     strategic
    0.68
     Workbook
    0.68
    POSITIVE LOGITS
     ethic
    0.96
    aday
    0.92
    坊
    0.89
    arounds
    0.88
    force
    0.87
    zeuge
    0.83
    ेच्छा
    0.80
     細胞
    0.79
    atche
    0.79
     лоша
    0.77
    Act Density 0.208%

    No Known Activations