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

    Neuronpedia

    INDEX
    Explanations

    words starting with col

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coloring
    0.99
    Color
    0.87
     torus
    0.83
     old
    0.83
     cysteine
    0.82
     Raceway
    0.82
     kind
    0.81
     coloration
    0.80
    ୟ
    0.80
     older
    0.79
    POSITIVE LOGITS
    quium
    1.04
    onial
    0.98
    umbus
    0.96
    ostrum
    0.94
    osseum
    0.93
    ोरेशन
    0.92
    ossal
    0.92
    UMNS
    0.90
    oscopy
    0.89
    嗚
    0.88
    Act Density 0.179%

    No Known Activations