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

    Neuronpedia

    INDEX
    Explanations

    help hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    2.72
    ある
    2.68
    См
    2.52
    ர்
    2.51
     Leider
    2.50
     dicha
    2.50
    হ
    2.49
     hechos
    2.47
    ेशन
    2.47
    𝑔
    2.38
    POSITIVE LOGITS
     brainchild
    3.36
    3.23
    ات
    3.12
    ikopter
    3.09
    ię
    3.02
    kę
    3.01
    mination
    2.90
    джа
    2.87
    UAGE
    2.84
    AED
    2.80
    Act Density 0.048%

    No Known Activations