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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.81
     granite
    -0.78
    ãĥ¼ãĥ³
    -0.69
    Ń·
    -0.68
     husband
    -0.67
     shelling
    -0.67
     lava
    -0.66
    ĻĤ
    -0.66
     grading
    -0.65
     Silva
    -0.65
    POSITIVE LOGITS
    initely
    0.85
    Definition
    0.83
    BIP
    0.82
    recogn
    0.80
    angible
    0.78
    Certain
    0.77
    Continue
    0.77
    Ability
    0.77
    Supp
    0.77
    Pac
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.