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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ذي
    -0.08
    �
    -0.07
    فش
    -0.07
    _orient
    -0.07
    ょう
    -0.06
     수강
    -0.06
     ดร
    -0.06
     detach
    -0.06
     igen
    -0.06
     Holden
    -0.06
    POSITIVE LOGITS
    _start
    0.07
    Video
    0.06
    .Ship
    0.06
    .y
    0.06
    -अ
    0.06
     �
    0.06
    Unsupported
    0.06
     friction
    0.06
    /articles
    0.06
    στο
    0.06
    Act Density 0.029%

    No Known Activations