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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parsing
    -0.07
     并
    -0.07
    ume
    -0.07
     MU
    -0.07
    VID
    -0.07
     commissioner
    -0.06
     Citadel
    -0.06
    .multiply
    -0.06
    notin
    -0.06
    dance
    -0.06
    POSITIVE LOGITS
     released
    0.07
     textured
    0.06
     Recogn
    0.06
     TypeError
    0.06
    udiantes
    0.06
     توسعه
    0.06
    ısında
    0.06
     крови
    0.06
    matrix
    0.06
     �
    0.06
    Act Density 0.071%

    No Known Activations