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
     estekak
    -0.48
    WEBPACK
    -0.47
     poils
    -0.46
     emporter
    -0.44
     demografica
    -0.44
    eneuve
    -0.43
    GMENT
    -0.43
    otene
    -0.42
    ptonshire
    -0.42
    enumi
    -0.41
    POSITIVE LOGITS
    */].
    0.72
     well
    0.60
     trajectories
    0.59
     trajectory
    0.59
    tagHelperRunner
    0.57
    UIControlState
    0.57
     whoſe
    0.56
    Seznam
    0.56
    iffion
    0.56
     audacity
    0.55
    Act Density 0.010%

    No Known Activations