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

    Neuronpedia

    INDEX
    Explanations

    cave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThanOr
    -0.08
    🅓
    -0.07
    ㉡
    -0.07
     tl
    -0.07
     @
    -0.07
    ʻ
    -0.07
    Were
    -0.07
    .read
    -0.07
    돌
    -0.07
     Exploration
    -0.07
    POSITIVE LOGITS
     cave
    0.09
    AVAILABLE
    0.08
    大学
    0.08
    廠
    0.08
     cavern
    0.07
     caves
    0.07
    מין
    0.07
     потребител
    0.07
    سكو
    0.07
    값
    0.07
    Act Density 0.004%

    No Known Activations