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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Proof
    0.52
     Proof
    0.47
    Savings
    0.46
    Approved
    0.46
    機構
    0.45
    Happy
    0.44
     grabbing
    0.44
    Agricultural
    0.43
    訨
    0.41
    Transformation
    0.41
    POSITIVE LOGITS
     MEM
    0.49
     embed
    0.45
     pai
    0.44
     kT
    0.44
     offline
    0.42
     Mem
    0.41
     goles
    0.40
     mT
    0.40
     membranes
    0.39
     Võ
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.