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

    Neuronpedia

    INDEX
    Explanations

    repetitive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shredded
    -0.08
    elian
    -0.08
     Moines
    -0.08
    iatr
    -0.08
     fresh
    -0.08
     Kali
    -0.08
    iaque
    -0.07
     Superman
    -0.07
     lion
    -0.07
     pile
    -0.07
    POSITIVE LOGITS
     تجاوز
    0.13
     vượt
    0.13
     dépasse
    0.12
     exceeded
    0.12
     surpass
    0.12
     overcome
    0.12
     surpassed
    0.12
     dépasser
    0.12
     превыш
    0.11
     exceed
    0.11
    Act Density 0.015%

    No Known Activations