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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ItemImage
    -0.78
    çĶ°
    -0.71
    utive
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
    iking
    -0.70
    VERTISEMENT
    -0.69
    selage
    -0.69
    UCT
    -0.66
    Mini
    -0.65
    å¿
    -0.65
    POSITIVE LOGITS
    power
    0.66
     Advertisement
    0.65
    igue
    0.65
    seeing
    0.64
     conqu
    0.63
     lockout
    0.62
    speak
    0.61
    powered
    0.61
    ables
    0.61
    /-
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.