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

    Neuronpedia

    INDEX
    Explanations

    from flower to fruit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    führen
    0.42
    紐
    0.41
     kõ
    0.39
    Profiling
    0.39
    quando
    0.38
     ROUILLER
    0.38
     limpar
    0.38
    ချုပ်
    0.38
     Passwort
    0.37
    wenn
    0.37
    POSITIVE LOGITS
     seeds
    0.42
     legumes
    0.40
     tetr
    0.39
     Princ
    0.39
     principles
    0.39
     pickles
    0.38
     accept
    0.38
     Accept
    0.38
     Acceptance
    0.38
     accepts
    0.37
    Act Density 0.001%

    No Known Activations