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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shout
    -0.06
    ^[
    -0.06
    did
    -0.06
    uf
    -0.06
    感恩
    -0.06
    روا
    -0.06
     Table
    -0.06
    Sales
    -0.06
    Fre
    -0.06
    _fx
    -0.06
    POSITIVE LOGITS
     kısa
    0.09
     Thailand
    0.08
    却不
    0.08
     possui
    0.08
    格會
    0.08
     Universität
    0.07
    憔
    0.07
     rationale
    0.07
    Петер
    0.07
     Hague
    0.07
    Act Density 0.080%

    No Known Activations