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

    Neuronpedia

    INDEX
    Explanations

    apple or explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mutation
    0.50
     mutagenesis
    0.45
    зина
    0.45
     mutant
    0.43
    сети
    0.42
    Manisha
    0.40
     mutagen
    0.39
    étel
    0.39
    UserState
    0.39
    genetic
    0.39
    POSITIVE LOGITS
    yfikacja
    0.39
     정사각형
    0.38
     ありがとう
    0.37
     Jes
    0.37
     Teacher
    0.37
     tuck
    0.37
     Frost
    0.37
     Pork
    0.37
     Do
    0.36
    櫒
    0.36
    Act Density 0.002%

    No Known Activations