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

    Neuronpedia

    INDEX
    Explanations

    ald

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ∈
    -0.08
     analyzes
    -0.07
    .Logic
    -0.07
     stabilization
    -0.07
     Bour
    -0.06
     Van
    -0.06
    窗
    -0.06
     Neuroscience
    -0.06
     _)
    -0.06
    DockControl
    -0.06
    POSITIVE LOGITS
     Emerald
    0.13
     Sapphire
    0.10
    apphire
    0.09
     Jade
    0.08
     Scarlet
    0.08
    Ruby
    0.08
    utm
    0.07
    atched
    0.07
    erald
    0.07
    ARS
    0.07
    Act Density 0.004%

    No Known Activations