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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    blood
    -0.74
    Shield
    -0.69
    shock
    -0.65
     Frost
    -0.65
    ities
    -0.64
    orest
    -0.63
     ______
    -0.63
    opathy
    -0.61
    orth
    -0.61
     Morrow
    -0.59
    POSITIVE LOGITS
    onga
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.82
    ãĤ´ãĥ³
    0.79
    ãĥĺãĥ©
    0.76
     sidx
    0.75
    mares
    0.74
    anmar
    0.73
     pse
    0.71
    dden
    0.71
    elight
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.