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

    Neuronpedia

    INDEX
    Explanations

    compact machinery and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schaden
    0.54
     Besuch
    0.46
     Geoffrey
    0.46
     décès
    0.46
     Associação
    0.46
    财产
    0.45
     immoral
    0.45
     Ombudsman
    0.45
     politische
    0.44
     हिंसा
    0.43
    POSITIVE LOGITS
     compact
    0.66
     optionally
    0.63
     selectable
    0.61
     chassis
    0.59
     lift
    0.59
     compactness
    0.59
     modular
    0.58
     prismatic
    0.57
     stabile
    0.57
     optional
    0.56
    Act Density 0.000%

    No Known Activations