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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cabinet
    -0.07
    465
    -0.07
     Batch
    -0.07
     preparation
    -0.07
     Runnable
    -0.06
    íme
    -0.06
     stay
    -0.06
    949
    -0.06
     PANEL
    -0.06
    추
    -0.06
    POSITIVE LOGITS
    .listener
    0.06
    .radians
    0.06
     pagina
    0.06
     persön
    0.06
     özg
    0.06
     Crimes
    0.06
    /lab
    0.06
     самого
    0.06
    Để
    0.06
     overlays
    0.06
    Act Density 0.033%

    No Known Activations