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

    Neuronpedia

    INDEX
    Explanations

    helping verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    merican
    -0.06
     deposited
    -0.06
    cimiento
    -0.06
     infants
    -0.06
     laz
    -0.06
     obtaining
    -0.06
    uffers
    -0.06
     trat
    -0.06
     restricted
    -0.06
     achieved
    -0.06
    POSITIVE LOGITS
    ради
    0.07
     مواط
    0.06
    ;↵↵↵↵↵
    0.06
     errores
    0.06
    ước
    0.06
    äm
    0.06
    aille
    0.06
     ».
    0.06
     DAMAGE
    0.06
     معل
    0.06
    Act Density 0.255%

    No Known Activations