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

    Neuronpedia

    INDEX
    Explanations

    Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    react
    0.83
     intellectuals
    0.82
     ఆధ్యాత్మిక
    0.72
    Love
    0.71
     scholars
    0.70
    पाक
    0.68
    Cr
    0.68
    ברים
    0.66
     сма
    0.64
    心を
    0.64
    POSITIVE LOGITS
     tre
    1.10
     Trevor
    1.06
     Tre
    1.05
    Tre
    0.95
     extractor
    0.87
     treble
    0.87
     eigenvector
    0.85
     TRE
    0.84
     Triathlon
    0.82
     trellis
    0.81
    Act Density 0.017%

    No Known Activations