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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Predicate
    -0.07
    Chan
    -0.07
     Sheldon
    -0.07
    ..."↵
    -0.07
     Porter
    -0.06
    Mais
    -0.06
     schl
    -0.06
    theory
    -0.06
    psi
    -0.06
    ENTRY
    -0.06
    POSITIVE LOGITS
     namedtuple
    0.07
    (lib
    0.06
     göre
    0.06
     mL
    0.06
     اك
    0.06
     predominant
    0.06
     meydana
    0.06
    AC
    0.06
     第一
    0.06
     painful
    0.06
    Act Density 0.001%

    No Known Activations