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

    Neuronpedia

    INDEX
    Explanations

    regular expressions and code snippets

    oai_token-act-pair · gemini-2.0-flash

    code and regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     termica
    -0.60
     étoit
    -0.58
    цездатний
    -0.56
     avoient
    -0.55
     auroit
    -0.54
    sizlik
    -0.54
     vediamo
    -0.54
     thermique
    -0.54
     debole
    -0.54
     prosthesis
    -0.53
    POSITIVE LOGITS
    ?\
    0.63
    ViewFeatures
    0.58
    ViewImports
    0.58
    ?,
    0.57
    曖昧さ回避
    0.57
    ?\\
    0.56
    GHIJKLM
    0.56
    {}",
    0.55
    ~,
    0.53
    viewDidLoad
    0.52
    Act Density 10.262%

    No Known Activations