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

    Neuronpedia

    INDEX
    Explanations

    life and world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     búsqueda
    0.59
     multitudes
    0.56
    мимо
    0.55
     gostaria
    0.54
    ку
    0.53
    க்
    0.53
     vínculos
    0.52
     corrobor
    0.52
     случаях
    0.51
     vínculo
    0.51
    POSITIVE LOGITS
     I
    0.80
    }
    0.59
     (
    0.57
     the
    0.56
     A
    0.55
     }
    0.54
    \
    0.52
     this
    0.51
    0
    0.49
     about
    0.49
    Act Density 0.941%

    No Known Activations