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

    Neuronpedia

    INDEX
    Explanations

    text color and highlighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॕ
    0.67
     adresse
    0.62
    ק
    0.62
     axles
    0.60
     Alphon
    0.60
     nhưng
    0.59
     inductance
    0.57
     indole
    0.57
     hinges
    0.56
     hiccups
    0.55
    POSITIVE LOGITS
     coloring
    0.66
    ed
    0.65
     colore
    0.61
     رنگ
    0.61
     kleuren
    0.59
    R
    0.59
     colouring
    0.58
    G
    0.55
    textcolor
    0.54
    ormap
    0.54
    Act Density 0.028%

    No Known Activations