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

    Neuronpedia

    INDEX
    Explanations

    however

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ),
    -0.06
    .con
    -0.06
    .Hide
    -0.06
    .,
    -0.06
    -cost
    -0.06
    vat
    -0.06
    Warn
    -0.06
    Collect
    -0.06
    .),
    -0.06
     bottleneck
    -0.06
    POSITIVE LOGITS
     however
    0.25
    however
    0.15
    -desktop
    0.08
     testim
    0.08
    iful
    0.07
    @if
    0.07
    (elem
    0.07
     Hughes
    0.07
    -story
    0.07
    calendar
    0.07
    Act Density 0.010%

    No Known Activations