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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rl
    0.34
    erdale
    0.33
    peanut
    0.33
    ;$
    0.33
    ការព
    0.33
    .$,
    0.32
    managers
    0.32
    हरियाणा
    0.32
    錡
    0.32
    ೊಳ್ಳ
    0.31
    POSITIVE LOGITS
    の
    0.38
     all
    0.35
    、
    0.33
    FAQs
    0.33
     চতুর্থ
    0.32
     more
    0.32
     fourth
    0.32
     specialized
    0.31
    க்
    0.31
     each
    0.31
    Act Density 0.263%

    No Known Activations