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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    Asking something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.85
    NameInMap
    -0.73
     Roskov
    -0.70
    ModelSerializer
    -0.68
    WithIOException
    -0.68
    RegressionTest
    -0.66
    pulumi
    -0.64
     ProtoMessage
    -0.63
     transfieras
    -0.60
     disparu
    -0.58
    POSITIVE LOGITS
     Fins
    0.42
    ruh
    0.41
    bia
    0.41
     siff
    0.41
    getWriter
    0.41
     ACI
    0.41
    MemoryWarning
    0.40
    ejs
    0.40
     liberality
    0.40
    ceğini
    0.39
    Act Density 1.418%

    No Known Activations