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

    Neuronpedia

    INDEX
    Explanations

    advice and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗍
    0.54
    💞
    0.54
     grayish
    0.53
    💖
    0.53
     whitish
    0.52
     sensorial
    0.52
    ਫ਼
    0.51
     sufferings
    0.50
    🆚
    0.50
    💟
    0.50
    POSITIVE LOGITS
     Warhammer
    0.63
     Wright
    0.59
     allowing
    0.57
     Eld
    0.54
     Stewart
    0.54
     देखील
    0.53
     Elliot
    0.53
     ব্যাবস্থা
    0.52
     ব্যপারে
    0.52
     Le
    0.52
    Act Density 0.080%

    No Known Activations