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

    Neuronpedia

    INDEX
    Explanations

    .util

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parade
    -0.07
    _days
    -0.06
     karma
    -0.06
     Waves
    -0.06
    opo
    -0.06
    iki
    -0.06
    comed
    -0.06
    太
    -0.06
    ,r
    -0.06
    ,tr
    -0.06
    POSITIVE LOGITS
     projectile
    0.07
    phalt
    0.06
    fight
    0.06
    อกาส
    0.06
     '↵
    0.06
    alpha
    0.06
     Dairy
    0.06
    _ATTRIB
    0.06
    >↵
    0.06
    ing
    0.06
    Act Density 0.059%

    No Known Activations