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

    Neuronpedia

    INDEX
    Explanations

    placeholders in professional communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tubules
    0.41
     multif
    0.38
     ensembles
    0.38
     excitations
    0.38
     genomes
    0.37
     convolution
    0.36
     ≈
    0.36
     primordial
    0.36
     palette
    0.36
     homogeneity
    0.36
    POSITIVE LOGITS
    nameof
    0.45
     nameof
    0.45
    用户名
    0.44
    CompanyName
    0.41
    钥匙
    0.40
    tagName
    0.40
    újo
    0.39
    your
    0.39
    Getenv
    0.39
    வர்
    0.39
    Act Density 0.027%

    No Known Activations