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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cascade
    -0.07
     avi
    -0.07
    .fil
    -0.07
     �
    -0.07
    IBC
    -0.06
    ayed
    -0.06
    TEGR
    -0.06
    urm
    -0.06
    editing
    -0.06
    _cm
    -0.06
    POSITIVE LOGITS
     uzavř
    0.07
     yup
    0.07
    _SCHEMA
    0.07
     ERA
    0.06
     expanding
    0.06
     Sta
    0.06
    .Mapper
    0.06
     dangerous
    0.06
     removeFromSuperview
    0.06
     empowering
    0.06
    Act Density 0.013%

    No Known Activations