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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cave
    -0.07
     JSON
    -0.06
    Cube
    -0.06
    .au
    -0.06
     Abuse
    -0.06
    bulk
    -0.06
     messages
    -0.06
     sabah
    -0.06
     behaviors
    -0.06
    ike
    -0.06
    POSITIVE LOGITS
    .Measure
    0.07
    .solution
    0.07
    .MONTH
    0.06
     periodo
    0.06
    .isLoggedIn
    0.06
    rir
    0.06
    単
    0.06
     така
    0.06
     WideString
    0.06
    ScreenState
    0.06
    Act Density 0.010%

    No Known Activations