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

    Neuronpedia

    INDEX
    Explanations

    code and abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cherchés
    -0.53
    الدراسه
    -0.51
    ResumeLayout
    -0.47
     Seeder
    -0.47
     titel
    -0.47
    GeneratedCode
    -0.46
    (&:
    -0.45
     billing
    -0.45
    Title
    -0.44
     exception
    -0.44
    POSITIVE LOGITS
     itſelf
    0.57
     protoimpl
    0.56
    MockBean
    0.56
    ętr
    0.55
    ening
    0.54
     cdti
    0.50
    TagMode
    0.50
    vary
    0.49
    ENDAR
    0.49
     Jefus
    0.49
    Act Density 0.000%

    No Known Activations