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

    Neuronpedia

    INDEX
    Explanations

    initializes or conditional `null`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     #(
    0.38
    Duration
    0.37
    Timestamp
    0.37
    ård
    0.36
    jeća
    0.36
    ⏫
    0.36
    Ar
    0.36
    ];//
    0.35
    órm
    0.35
    Top
    0.35
    POSITIVE LOGITS
     முடியவில்லை
    0.41
     terrier
    0.40
     ne
    0.38
     neoprene
    0.38
     poder
    0.38
    plates
    0.37
     sushi
    0.37
     Пас
    0.37
     sender
    0.37
     hmm
    0.37
    Act Density 0.002%

    No Known Activations