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

    Neuronpedia

    INDEX
    Explanations

    u

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -shared
    -0.07
    stddef
    -0.06
    нг
    -0.06
     Laboratories
    -0.06
     Eş
    -0.06
     CFR
    -0.06
     Spider
    -0.06
    โจ
    -0.06
     forgotten
    -0.06
     Ah
    -0.06
    POSITIVE LOGITS
    ours
    0.07
     REGARD
    0.07
    ΑΚ
    0.07
    imitives
    0.06
    ování
    0.06
    ród
    0.06
    !";↵
    0.06
     loser
    0.06
     cray
    0.06
    (pages
    0.06
    Act Density 0.000%

    No Known Activations