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

    Neuronpedia

    INDEX
    Explanations

    16

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimal
    -0.07
     ();
↵
    -0.07
     bump
    -0.07
    CBS
    -0.06
     bumps
    -0.06
     tendency
    -0.06
     Fly
    -0.06
     antioxid
    -0.06
    'I
    -0.06
    Button
    -0.06
    POSITIVE LOGITS
    16
    0.10
    swagen
    0.08
    416
    0.07
    UNS
    0.07
    $MESS
    0.07
    016
    0.07
    ASP
    0.06
    Connecting
    0.06
    160
    0.06
    316
    0.06
    Act Density 0.032%

    No Known Activations