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

    Neuronpedia

    INDEX
    Explanations

    trace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enlargement
    -0.08
    Facing
    -0.08
     symmetrical
    -0.08
     temática
    -0.07
     nova
    -0.07
    Greg
    -0.07
    Bes
    -0.07
     Nash
    -0.07
    Adjustment
    -0.07
    faces
    -0.07
    POSITIVE LOGITS
     Tracking
    0.19
     tracking
    0.19
    Tracking
    0.16
    _tracking
    0.16
     tracing
    0.15
     provenance
    0.14
    踪
    0.14
     tracked
    0.14
     TRACK
    0.14
    tracking
    0.13
    Act Density 0.021%

    No Known Activations