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

    Neuronpedia

    INDEX
    Explanations

    512

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    네요
    -0.08
    .show
    -0.07
     intuit
    -0.07
    훈
    -0.07
     просто
    -0.07
    neighbor
    -0.07
    nings
    -0.07
    �
    -0.07
     reviews
    -0.07
    versation
    -0.06
    POSITIVE LOGITS
    (tm
    0.08
    ];
↵
    0.06
    (svg
    0.06
    мі
    0.06
     παν
    0.06
     þ
    0.06
    igmatic
    0.06
     dispens
    0.06
     CACHE
    0.06
     @$
    0.06
    Act Density 0.016%

    No Known Activations