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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    烔
    0.39
    льку
    0.38
    klady
    0.36
    hteet
    0.36
    ittaa
    0.36
    žiť
    0.35
    ӓ
    0.35
    如同
    0.34
    ittu
    0.34
    zijde
    0.34
    POSITIVE LOGITS
    dotted
    0.38
    ᆻ
    0.37
    )}^{\
    0.36
    dense
    0.36
    的話
    0.36
    øre
    0.35
     denen
    0.34
    who
    0.34
     carg
    0.34
     controle
    0.34
    Act Density 0.035%

    No Known Activations