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

    Neuronpedia

    INDEX
    Explanations

    route parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strict
    0.37
     coefficient
    0.36
    成り
    0.35
    roughs
    0.35
     preserve
    0.35
     sticky
    0.34
     сю
    0.34
     endowed
    0.34
     display
    0.33
    άζ
    0.33
    POSITIVE LOGITS
    Find
    0.49
    Linkedin
    0.43
    Tweet
    0.41
    Turbo
    0.39
    Params
    0.38
    find
    0.38
     Find
    0.38
    FIND
    0.38
    হ্যালো
    0.38
     Spir
    0.38
    Act Density 0.001%

    No Known Activations