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

    Neuronpedia

    INDEX
    Explanations

    commands with !

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accél
    0.43
     bitches
    0.41
     accelerating
    0.39
    ﻉ
    0.39
     evaluate
    0.39
     Analyze
    0.38
    ﻑ
    0.38
     misura
    0.38
     Evaluate
    0.38
    WORK
    0.38
    POSITIVE LOGITS
    缠
    0.40
     предме
    0.38
     იმ
    0.38
    highlight
    0.38
     highlight
    0.37
     legend
    0.36
     Standards
    0.35
     sighted
    0.35
    <iframe>
    0.35
    Highlight
    0.35
    Act Density 0.000%

    No Known Activations