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

    Neuronpedia

    INDEX
    Explanations

    code, errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alumni
    -0.06
     conductor
    -0.06
     worship
    -0.06
     cougar
    -0.06
     addUser
    -0.06
     springfox
    -0.06
    .brand
    -0.06
    في
    -0.06
    Guardar
    -0.05
     является
    -0.05
    POSITIVE LOGITS
     incentives
    0.07
    싸
    0.07
     RIGHTS
    0.07
     stimulates
    0.06
     storms
    0.06
    .COMP
    0.06
    atorium
    0.06
    ecc
    0.06
     cynical
    0.06
     Ext
    0.06
    Act Density 0.006%

    No Known Activations