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

    Neuronpedia

    INDEX
    Explanations

    syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝚟
    0.39
    ത്തിയാ
    0.38
    ندق
    0.38
     granola
    0.38
    ╕
    0.37
    إذا
    0.37
     machining
    0.36
    lensFlare
    0.36
     রাধানাথ
    0.36
    afd
    0.36
    POSITIVE LOGITS
     HIG
    0.39
     linear
    0.38
     ind
    0.38
    TER
    0.38
     শীর্ষে
    0.38
    ISAM
    0.38
     DEFAULT
    0.37
    監
    0.37
    ଶ
    0.36
    CRE
    0.36
    Act Density 0.001%

    No Known Activations