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

    Neuronpedia

    INDEX
    Explanations

    players or audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mortars
    0.46
     pellet
    0.44
     parole
    0.43
     pall
    0.42
    folg
    0.41
     cloak
    0.41
    𝕦
    0.40
     меха
    0.40
     gest
    0.40
     σημα
    0.40
    POSITIVE LOGITS
     साय
    0.40
    <h2>
    0.38
    archive
    0.37
    <h3>
    0.37
    Ŝ
    0.37
     Easily
    0.37
    players
    0.36
    jeux
    0.35
     کیسینو
    0.34
    ließlich
    0.34
    Act Density 0.000%

    No Known Activations