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

    Neuronpedia

    INDEX
    Explanations

    user prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewUrl
    0.41
     fewer
    0.39
     hereunder
    0.39
    ــــــــ
    0.38
     reproductions
    0.38
    ewer
    0.38
     progressions
    0.38
     elementów
    0.38
     tendencies
    0.37
     Trip
    0.37
    POSITIVE LOGITS
     Originally
    0.44
     avatar
    0.43
    äjä
    0.43
    avatar
    0.42
    Originally
    0.42
    yeah
    0.41
     원래
    0.40
    Eisen
    0.39
    语气
    0.39
    Koi
    0.39
    Act Density 0.002%

    No Known Activations