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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ONY
    -0.72
     reproduce
    -0.70
    bats
    -0.66
    ACY
    -0.66
    hawk
    -0.63
    skinned
    -0.63
    oning
    -0.63
    ãĥİ
    -0.63
    interstitial
    -0.62
    IRE
    -0.62
    POSITIVE LOGITS
    insula
    0.68
    pocket
    0.66
     reven
    0.64
     Relief
    0.64
    tube
    0.63
    lycer
    0.62
    uyomi
    0.61
    gear
    0.61
     payroll
    0.60
    ricks
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.