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

    Neuronpedia

    INDEX
    Explanations

    programming code and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.30
     .
    0.28
    :
    0.26
    ™.
    0.23
    ].
    0.22
    .)
    0.22
     nécessite
    0.22
    .]
    0.21
     	i
    0.21
     begitu
    0.21
    POSITIVE LOGITS
    as
    0.25
    for
    0.24
    when
    0.23
     حق
    0.23
    an
    0.22
    ل
    0.21
    మా
    0.21
    w
    0.21
    }$,
    0.20
    పూర్
    0.20
    Act Density 2.004%

    No Known Activations