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

    Neuronpedia

    INDEX
    Explanations

    summarizing differences in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कर्मचारी
    0.73
     આરોપી
    0.68
    Help
    0.67
    drop
    0.66
    וא
    0.65
     कर्मचारियों
    0.65
     سي
    0.64
     Bell
    0.63
    Besch
    0.63
    tay
    0.62
    POSITIVE LOGITS
    fz
    0.83
    pz
    0.79
     mechanistic
    0.78
    RANGER
    0.76
     dez
    0.76
     Dex
    0.76
    zun
    0.75
     jul
    0.75
    сера
    0.75
     irony
    0.75
    Act Density 0.005%

    No Known Activations