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

    Neuronpedia

    INDEX
    Explanations

    nearby or critical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     critical
    -1.18
    critical
    -1.13
    Critical
    -0.98
     nearby
    -0.98
     Critical
    -0.85
    nearby
    -0.85
     CRITICAL
    -0.82
     critically
    -0.79
    CRITICAL
    -0.78
     Nearby
    -0.75
    POSITIVE LOGITS
    jsxFileName
    0.59
     Realt
    0.54
     NCS
    0.53
    verwijspagina
    0.52
     Warn
    0.52
     Avent
    0.52
    oplayer
    0.52
    casian
    0.51
    NewUrlParser
    0.51
     Cres
    0.49
    Act Density 0.590%

    No Known Activations