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

    Neuronpedia

    INDEX
    Explanations

    mentions of news and journalistic media

    oai_token-act-pair · gemini-2.0-flash

    BBC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     >=",
    -0.67
    istice
    -0.59
     bVar
    -0.55
    StructEnd
    -0.52
    zeera
    -0.50
     podjela
    -0.50
    fabricated
    -0.47
    aarrggbb
    -0.46
    cod
    -0.46
     (!__
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.75
    حوالہ
    0.71
    AnchorStyles
    0.69
     صوتيه
    0.68
     <<<<<<<<<<<<<<
    0.60
    /**
    0.58
    \{\\
    0.58
    发表于
    0.53
    DockStyle
    0.53
    RegressionTest
    0.52
    Act Density 2.627%

    No Known Activations