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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licts
    -0.07
     Saud
    -0.07
     아버지
    -0.07
     inequalities
    -0.06
     synchronous
    -0.06
     його
    -0.06
    ynchronous
    -0.06
    ่าอ
    -0.06
    ολ
    -0.06
    America
    -0.06
    POSITIVE LOGITS
    !↵↵↵↵
    0.07
    .world
    0.07
     #↵↵
    0.06
    	cfg
    0.06
     Spotify
    0.06
    _added
    0.06
     );
↵
    0.06
    (',
    0.06
     перв
    0.06
    !..
    0.06
    Act Density 0.000%

    No Known Activations