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

    Neuronpedia

    INDEX
    Explanations

    verse or quotation delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പ്രവർത്തന
    0.35
     molds
    0.34
     delimiters
    0.34
     shaders
    0.34
    乆
    0.33
     fonctions
    0.33
     شكل
    0.33
     بشكل
    0.33
     الس
    0.32
     conformance
    0.32
    POSITIVE LOGITS
    ell
    0.43
    le
    0.40
    ed
    0.39
    pe
    0.39
    ard
    0.39
    end
    0.38
    aka
    0.37
    ely
    0.36
    he
    0.36
    uk
    0.35
    Act Density 0.001%

    No Known Activations