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

    Neuronpedia

    INDEX
    Explanations

    on such / with difficult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.23
    K
    0.21
     दुष्प्रभाव
    0.20
    DAS
    0.20
    reiche
    0.20
     высокая
    0.19
    を中心
    0.19
     млрд
    0.19
    F
    0.19
     अथवा
    0.19
    POSITIVE LOGITS
     the
    0.40
     this
    0.35
     things
    0.34
     it
    0.33
     what
    0.33
     your
    0.28
     them
    0.28
     stories
    0.27
     cosas
    0.26
     its
    0.25
    Act Density 0.879%

    No Known Activations