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

    Neuronpedia

    INDEX
    Explanations

    dimensions and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RoutingModule
    0.64
    routing
    0.47
    RouterModule
    0.45
    MINUTE
    0.44
    VIII
    0.43
     RouterModule
    0.42
    FormsModule
    0.41
    اً
    0.40
    NgModule
    0.38
    블릿
    0.37
    POSITIVE LOGITS
     subject
    1.01
     Subject
    0.96
    Subject
    0.91
    subject
    0.89
     Behavior
    0.80
    Behavior
    0.75
     SUBJECT
    0.75
     subjects
    0.72
     subiect
    0.72
     sujeto
    0.71
    Act Density 0.009%

    No Known Activations