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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cup
    -0.07
    iven
    -0.07
    ide
    -0.07
    BN
    -0.07
    mutation
    -0.07
    -0.07
    λα
    -0.06
     CAD
    -0.06
    ybrid
    -0.06
     cyn
    -0.06
    POSITIVE LOGITS
    ても
    0.06
     TInt
    0.06
     absl
    0.06
    .createdAt
    0.06
    .previous
    0.06
     rgba
    0.06
     aluno
    0.06
    ，都
    0.06
     ApplicationRecord
    0.06
     NgModule
    0.06
    Act Density 0.083%

    No Known Activations