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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     formation
    -0.70
     Submission
    -0.70
     Competition
    -0.68
    aceous
    -0.68
    umers
    -0.66
     pursuit
    -0.63
     genetics
    -0.62
    odan
    -0.60
     Username
    -0.59
    ModLoader
    -0.58
    POSITIVE LOGITS
    tons
    0.81
    NetMessage
    0.75
    å§
    0.74
    fully
    0.71
    enture
    0.71
    gency
    0.69
     lia
    0.68
    pher
    0.68
    sg
    0.68
    ha
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.