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

    Neuronpedia

    INDEX
    Explanations

    Snowden, p-value, my ultimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    1.54
    中
    1.36
    การ
    1.32
    restrict
    1.28
    WriteLine
    1.27
     poached
    1.17
    switchTo
    1.17
     mutton
    1.16
    ovable
    1.15
    findings
    1.15
    POSITIVE LOGITS
    età
    1.40
    ıyordu
    1.24
    त्कार
    1.21
    тын
    1.19
     \%$
    1.18
    áf
    1.14
    త్య
    1.14
    тие
    1.14
    ༸
    1.12
    %$
    1.12
    Act Density 0.001%

    No Known Activations