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

    Neuronpedia

    INDEX
    Explanations

    html document start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लाय
    0.87
    Jason
    0.80
    潟
    0.80
    password
    0.79
    Dash
    0.77
    aran
    0.77
    Password
    0.76
    [][
    0.75
    Stephen
    0.75
    답니다
    0.73
    POSITIVE LOGITS
     blasting
    0.87
     diminishing
    0.83
     forcible
    0.80
     torment
    0.77
     exerting
    0.76
     iterates
    0.76
     overwhelming
    0.74
     bur
    0.74
     forcing
    0.74
     fighting
    0.73
    Act Density 0.027%

    No Known Activations