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

    Neuronpedia

    INDEX
    Explanations

    get ready to start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cán
    0.71
     überall
    0.70
     broadly
    0.68
    궤
    0.68
    辕
    0.66
     `>=
    0.66
     commitments
    0.66
     Aha
    0.66
    晤
    0.66
     anywhere
    0.65
    POSITIVE LOGITS
     Ready
    1.05
    Ready
    1.01
     ready
    1.01
    ready
    0.95
     lost
    0.85
    lost
    0.81
     active
    0.73
    Lost
    0.72
    ogl
    0.71
     Prepared
    0.69
    Act Density 0.052%

    No Known Activations