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

    Neuronpedia

    INDEX
    Explanations

    envy or wanting to be like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rollers
    -0.07
    Subviews
    -0.06
     cameo
    -0.06
    +z
    -0.06
    Pet
    -0.06
    -scal
    -0.06
     itemView
    -0.06
     Duc
    -0.05
    -have
    -0.05
     damages
    -0.05
    POSITIVE LOGITS
    BUFFER
    0.08
    .Networking
    0.07
     BLE
    0.07
    SPI
    0.07
     Bosch
    0.07
    inter
    0.06
    避
    0.06
     kur
    0.06
    änder
    0.06
     attravers
    0.06
    Act Density 0.050%

    No Known Activations