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

    Neuronpedia

    INDEX
    Explanations

    nature or audio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.63
    u
    1.59
    да
    1.37
    пер
    1.32
    𝙛
    1.31
    дық
    1.30
    ers
    1.30
     деко
    1.27
    letzt
    1.26
    त
    1.25
    POSITIVE LOGITS
    𝗥
    2.05
     rápidamente
    2.04
    𝗰
    2.01
    ერის
    1.99
    rimiento
    1.90
    ◃
    1.89
    𝗲
    1.85
     katanya
    1.84
     surgi
    1.80
    𝗖
    1.78
    Act Density 0.000%

    No Known Activations