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

    Neuronpedia

    INDEX
    Explanations

    person titles and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maths
    0.45
     startTime
    0.41
     ничего
    0.38
     gant
    0.38
     Dino
    0.37
     waistband
    0.37
     KM
    0.37
     Filippo
    0.37
    豌
    0.35
     whole
    0.35
    POSITIVE LOGITS
    嗡
    0.41
    textbackslash
    0.41
     कहें
    0.38
    mathbb
    0.38
    Thro
    0.37
    ete
    0.37
    ')->
    0.36
    lah
    0.36
    Te
    0.35
    OVE
    0.35
    Act Density 0.000%

    No Known Activations