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

    Neuronpedia

    INDEX
    Explanations

    outputs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scripts
    0.77
     script
    0.76
     Script
    0.75
    Script
    0.70
    理論
    0.68
     Scripts
    0.67
     rodas
    0.66
     scripting
    0.65
    ডিং
    0.64
     Urdu
    0.64
    POSITIVE LOGITS
    Outputs
    0.88
     Outputs
    0.84
     outputs
    0.80
     Vard
    0.71
     স্থানীয়
    0.70
    bier
    0.66
    Monica
    0.65
    output
    0.65
     Output
    0.65
    outputs
    0.65
    Act Density 0.031%

    No Known Activations