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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     摩
    -0.10
     moviment
    -0.09
    摩
    -0.09
     TNT
    -0.08
     발전
    -0.08
     theoret
    -0.08
     geg
    -0.08
     Bewegung
    -0.08
     mos
    -0.08
     dynamics
    -0.08
    POSITIVE LOGITS
    Palindrome
    0.10
     voldoet
    0.09
    Requirement
    0.09
     requisito
    0.08
     palindrome
    0.08
     abiding
    0.08
     violates
    0.08
     erfüllt
    0.08
     Apparently
    0.08
    Predicate
    0.08
    Act Density 0.004%

    No Known Activations