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

    Neuronpedia

    INDEX
    Explanations

    yields and plantuml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ________________
    0.40
    BODY
    0.39
    Turns
    0.38
    body
    0.37
    </b>
    0.36
    clock
    0.36
    wooden
    0.36
    mother
    0.34
     நகர
    0.34
     indiqué
    0.34
    POSITIVE LOGITS
    ۊ
    0.37
     -,
    0.37
     (!)
    0.36
     deline
    0.36
     egip
    0.34
    dsale
    0.34
     ionic
    0.34
     intuit
    0.34
    回事
    0.33
     thailand
    0.33
    Act Density 0.001%

    No Known Activations