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

    Neuronpedia

    INDEX
    Explanations

    topics, copyright notices, forum posts

    np_acts-logits-general · gemini-2.5-flash-lite

    First item or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    you
    0.38
     It
    0.37
    ORF
    0.37
    ानी
    0.36
    Zeros
    0.36
    (
    0.36
    It
    0.36
    HHHH
    0.36
    tering
    0.36
    Dreams
    0.35
    POSITIVE LOGITS
     którym
    0.50
    ও
    0.49
    在
    0.49
     σε
    0.47
     in
    0.44
     second
    0.44
    ла
    0.42
    са
    0.42
    த்தில்
    0.42
    у
    0.42
    Act Density 1.300%

    No Known Activations