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

    Neuronpedia

    INDEX
    Explanations

    Code/technical fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bar
    -0.07
     Trim
    -0.07
     Calif
    -0.07
    .field
    -0.07
     Ctrl
    -0.07
    .lin
    -0.06
     prof
    -0.06
     Tory
    -0.06
    toUpperCase
    -0.06
    ibNameOrNil
    -0.06
    POSITIVE LOGITS
    GN
    0.07
     من
    0.06
     durability
    0.06
    °C
    0.06
     Anders
    0.06
    153
    0.06
    venth
    0.06
     경
    0.06
     carro
    0.06
     digestion
    0.06
    Act Density 0.000%

    No Known Activations