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

    Neuronpedia

    INDEX
    Explanations

    sentinel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     albums
    -0.08
     LF
    -0.07
    delivr
    -0.07
     album
    -0.06
     χω
    -0.06
    $params
    -0.06
     grandson
    -0.06
    _probability
    -0.06
    Boom
    -0.06
    >{$
    -0.06
    POSITIVE LOGITS
     sentinel
    0.18
     Sentinel
    0.14
     Sentry
    0.11
    inel
    0.09
    enti
    0.08
    etler
    0.07
     I
    0.07
     Guardian
    0.07
     guardian
    0.07
    incinn
    0.07
    Act Density 0.001%

    No Known Activations