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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    りに
    -0.08
    int
    -0.07
    čila
    -0.07
    isher
    -0.07
    ppard
    -0.07
     tourism
    -0.06
    washer
    -0.06
     Minds
    -0.06
    WebView
    -0.06
    OfClass
    -0.06
    POSITIVE LOGITS
     Hydraulic
    0.06
    NotificationCenter
    0.06
    ubernetes
    0.06
    _RE
    0.06
     forState
    0.06
     combustion
    0.06
     Lou
    0.06
     drv
    0.06
    FormControl
    0.06
    贫
    0.06
    Act Density 0.096%

    No Known Activations