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

    Neuronpedia

    INDEX
    Explanations

    Mechanical controls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Patterns
    -0.07
     RD
    -0.07
     �
    -0.06
     trends
    -0.06
    _Profile
    -0.06
    otide
    -0.06
    content
    -0.06
    Beam
    -0.06
     costing
    -0.06
    Salary
    -0.06
    POSITIVE LOGITS
    BUTTONDOWN
    0.07
     dictionaryWith
    0.07
    0.06
    snow
    0.06
     dzie
    0.06
    _sprites
    0.06
    (strpos
    0.06
     yöntem
    0.06
     �
    0.06
    생님
    0.06
    Act Density 0.049%

    No Known Activations