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

    Neuronpedia

    INDEX
    Explanations

    cues related to structured data formats and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or data with unicode characters and underscores

    np_acts-logits-general · gemini-2.0-flash

    the letter u

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.63
    లాలు
    -0.57
     grpc
    -0.52
     فريبيس
    -0.51
     архивлан
    -0.50
    Personendaten
    -0.50
    DockStyle
    -0.49
    ніципалі
    -0.49
    PerformLayout
    -0.47
     protoimpl
    -0.46
    POSITIVE LOGITS
     u
    1.94
    u
    1.91
     у
    1.05
     unit
    1.05
     uLocal
    0.97
     units
    0.93
    у
    0.92
    unit
    0.91
     U
    0.91
    U
    0.90
    Act Density 0.314%

    No Known Activations