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

    Neuronpedia

    INDEX
    Explanations

    dialogue, code, and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ownie
    1.34
    ulich
    1.31
    otri
    1.25
    cita
    1.24
    ali
    1.23
    yz
    1.23
    unat
    1.23
    arak
    1.23
     bary
    1.22
    iraju
    1.21
    POSITIVE LOGITS
     идеи
    1.16
    规模
    1.14
    以便
    1.13
     sangue
    1.12
     ця
    1.11
    Amanda
    1.11
     Danmark
    1.10
     склада
    1.10
     الجزائر
    1.10
    /////////
    1.08
    Act Density 0.008%

    No Known Activations