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

    Neuronpedia

    INDEX
    Explanations

    returning or coming back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    1.24
    ä
    0.99
    -
    0.91
    &
    0.91
    \
    0.79
     proveedor
    0.78
    ע
    0.77
     compartir
    0.75
     transportar
    0.73
     realizar
    0.72
    POSITIVE LOGITS
     Back
    0.86
    ্রমে
    0.86
     Retour
    0.86
     terug
    0.83
     zurück
    0.82
     लौट
    0.81
    ция
    0.80
     indietro
    0.80
    返す
    0.80
     लौटे
    0.80
    Act Density 0.272%

    No Known Activations