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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.31
     শাসকদের
    0.30
    𝒉
    0.29
    माष्टमी
    0.28
     Minecraft
    0.28
     Sebelum
    0.28
    серва
    0.27
    కపో
    0.27
    کز
    0.27
     Cretaceous
    0.27
    POSITIVE LOGITS
    .
    0.31
     co
    0.29
    me
    0.29
    5
    0.27
     मै
    0.26
     a
    0.26
    ;
    0.25
     coworker
    0.25
     le
    0.24
     com
    0.24
    Act Density 0.094%

    No Known Activations