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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rapper
    -0.08
    ISODE
    -0.07
    ELY
    -0.07
    ENU
    -0.07
    ﺊ
    -0.07
    iry
    -0.07
     DISABLE
    -0.07
    /Header
    -0.07
    ᆞ
    -0.07
     loyal
    -0.07
    POSITIVE LOGITS
     subt
    0.08
    绪
    0.07
    pattern
    0.07
     smtp
    0.07
     Metropolitan
    0.07
    מיכה
    0.07
     delimited
    0.07
     Watkins
    0.06
     tapered
    0.06
     nic
    0.06
    Act Density 0.000%

    No Known Activations