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

    Neuronpedia

    INDEX
    Explanations

    sensitive information or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magn
    0.48
    이다
    0.45
     fable
    0.45
     Fabio
    0.45
     vacanam
    0.44
     Addison
    0.43
    riz
    0.43
     temple
    0.42
     parable
    0.42
     Así
    0.42
    POSITIVE LOGITS
    等が
    0.49
    brane
    0.48
    国外
    0.45
    粆
    0.45
    ⵕ
    0.44
     licenses
    0.42
    ১
    0.42
     сотруд
    0.42
    +')
    0.42
    籶
    0.42
    Act Density 0.006%

    No Known Activations