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

    Neuronpedia

    INDEX
    Explanations

    URI paths and encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.24
    ה
    1.20
     Emulator
    1.18
     Invoke
    1.14
    מ
    1.13
     Intersection
    1.12
     Compute
    1.10
    ור
    1.09
    И
    1.06
     Helps
    1.05
    POSITIVE LOGITS
    lift
    1.38
    thinking
    1.30
    Rivers
    1.26
    lifting
    1.25
    ிய
    1.22
    िटी
    1.22
    amond
    1.17
     avocat
    1.17
    suited
    1.16
    iation
    1.16
    Act Density 0.538%

    No Known Activations