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

    Neuronpedia

    INDEX
    Explanations

    boiling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thèse
    -0.07
    𬹼
    -0.07
     perhaps
    -0.06
    픠
    -0.06
    (map
    -0.06
    �
    -0.06
    stairs
    -0.06
    ऋ
    -0.06
    🤰
    -0.06
     الإلكترو
    -0.06
    POSITIVE LOGITS
    Caption
    0.07
    Pragma
    0.07
    freq
    0.07
     Tenn
    0.07
    いで
    0.07
    民众
    0.07
    onen
    0.07
    .rf
    0.07
     Colony
    0.06
     approve
    0.06
    Act Density 0.002%

    No Known Activations