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

    Neuronpedia

    INDEX
    Explanations

    Technical/science jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ní
    -0.07
     ambos
    -0.07
     ως
    -0.07
    466
    -0.07
     nause
    -0.06
     Buster
    -0.06
     containing
    -0.06
     Rita
    -0.06
     chute
    -0.06
     Rwanda
    -0.06
    POSITIVE LOGITS
    OOD
    0.08
    .In
    0.06
     Rooney
    0.06
     長
    0.06
    素
    0.06
    IGIN
    0.06
    猫
    0.06
    _CODE
    0.06
    -field
    0.06
     Information
    0.06
    Act Density 0.000%

    No Known Activations