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

    Neuronpedia

    INDEX
    Explanations

    web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.89
    ↵↵
    0.75
    ↵
    0.75
    0.73
    ultimate
    0.58
    ified
    0.56
     for
    0.55
    i
    0.54
     We
    0.53
     and
    0.52
    POSITIVE LOGITS
    nbhost
    1.31
     亻
    1.31
    第壹百
    1.28
    textfield
    1.26
    /////////////
    1.25
     ponds
    1.25
     peristiwa
    1.24
    bandage
    1.24
    狯
    1.23
     morn
    1.23
    Act Density 0.096%

    No Known Activations