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

    Neuronpedia

    INDEX
    Explanations

    say "ine" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikut
    -0.07
    猢
    -0.07
    ้าน
    -0.06
    辽宁
    -0.06
    trzymać
    -0.06
    ƛ
    -0.06
    ulumi
    -0.06
    �
    -0.06
     Fulton
    -0.06
    enticator
    -0.06
    POSITIVE LOGITS
    应该
    0.07
    FileInfo
    0.07
     Tracker
    0.07
     investing
    0.07
     Bias
    0.07
    ACCESS
    0.06
    agment
    0.06
    年纪
    0.06
    Happy
    0.06
    sha
    0.06
    Act Density 0.016%

    No Known Activations