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

    Neuronpedia

    INDEX
    Explanations

    inherent rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ឺ
    0.42
    X
    0.41
    链接
    0.41
    Ident
    0.40
    Cross
    0.39
    ϵ
    0.38
    Cluster
    0.38
    ба
    0.38
    Dh
    0.38
    海上
    0.38
    POSITIVE LOGITS
     weaken
    0.48
     aggravate
    0.45
    䒿
    0.43
     abatement
    0.42
     extortion
    0.42
     callous
    0.41
     slander
    0.41
     exacerbate
    0.41
     usurp
    0.41
     purview
    0.41
    Act Density 0.005%

    No Known Activations