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

    Neuronpedia

    INDEX
    Explanations

    prove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.64
     leg
    -0.63
    djangoproject
    -0.61
    dibles
    -0.59
     createState
    -0.59
    DockStyle
    -0.51
     nawr
    -0.49
     Jazeera
    -0.48
     DIR
    -0.48
     Vz
    -0.48
    POSITIVE LOGITS
     Ground
    0.73
    Ground
    0.68
     Grounds
    0.67
    Grounded
    0.62
     ModelExpression
    0.59
    AndroidJUnit
    0.58
    GMP
    0.58
     GROUND
    0.58
    grounds
    0.54
    MemoryWarning
    0.52
    Act Density 0.003%

    No Known Activations