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

    Neuronpedia

    INDEX
    Explanations

    statement terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Airt
    0.35
     Talking
    0.32
     Denver
    0.32
     Cortex
    0.32
     outbound
    0.31
     olmadan
    0.31
     Hiring
    0.31
     Optics
    0.30
     wordpress
    0.30
     Hartford
    0.30
    POSITIVE LOGITS
    ྪ
    0.38
     \"%
    0.36
    ადგენ
    0.34
    étaire
    0.34
     покри
    0.33
    ervlak
    0.33
    knie
    0.33
     стали
    0.33
    assurer
    0.33
    ើន
    0.33
    Act Density 0.008%

    No Known Activations