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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Т
    -0.07
     �
    -0.07
    'name
    -0.07
     HOW
    -0.06
    >>
    -0.06
    eq
    -0.06
    -light
    -0.06
    []{"
    -0.06
     tener
    -0.06
     DEAL
    -0.06
    POSITIVE LOGITS
    .Suppress
    0.07
    blink
    0.07
    Brush
    0.06
    .Assert
    0.06
    ToDevice
    0.06
     Cumberland
    0.06
     Basil
    0.06
     skip
    0.06
     Skip
    0.06
     Crimson
    0.06
    Act Density 0.005%

    No Known Activations