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

    Neuronpedia

    INDEX
    Explanations

    code documentation and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     äuß
    0.99
    professor
    0.96
    采访
    0.88
     Frage
    0.88
     rövid
    0.86
    Чем
    0.86
     definitiv
    0.86
     wynika
    0.86
     theor
    0.85
     दिखाई
    0.84
    POSITIVE LOGITS
     command
    0.66
     configuration
    0.64
     permissions
    0.59
     custom
    0.59
     layouts
    0.58
     user
    0.57
     commands
    0.57
     encoding
    0.56
     namespaces
    0.56
     workflow
    0.56
    Act Density 0.189%

    No Known Activations