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

    Neuronpedia

    INDEX
    Explanations

    as, say, like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     причина
    0.29
     Into
    0.26
    ंसाठी
    0.25
     wichtig
    0.25
     importancia
    0.25
    ému
    0.25
     bisogna
    0.24
     raisons
    0.24
     করায়
    0.24
     треба
    0.23
    POSITIVE LOGITS
    ¬
    0.32
    і
    0.30
    C
    0.29
    一些
    0.29
    ż
    0.29
    '
    0.27
    ‚
    0.27
    of
    0.27
     ¬
    0.27
    {\'
    0.26
    Act Density 0.088%

    No Known Activations