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

    Neuronpedia

    INDEX
    Explanations

    hour markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     streng
    -0.70
    ggplot
    -0.70
    strength
    -0.69
    Selective
    -0.69
     Jennie
    -0.69
    ↵
    -0.69
    etron
    -0.68
     blister
    -0.67
     Vra
    -0.67
    [^
    -0.66
    POSITIVE LOGITS
     marker
    2.78
     markers
    2.53
    marker
    2.34
     Marker
    2.34
    Marker
    2.13
    markers
    2.05
     Markers
    2.02
    Markers
    1.91
     mark
    1.69
    MARKER
    1.63
    Act Density 0.036%

    No Known Activations