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

    Neuronpedia

    INDEX
    Explanations

    preventing negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dương
    0.48
     generously
    0.48
     unable
    0.47
     functions
    0.46
     germanium
    0.45
    ಸ್ಕೊ
    0.44
     patience
    0.44
     ทด
    0.44
     geometri
    0.44
     handkerchief
    0.44
    POSITIVE LOGITS
    injury
    0.72
     abuses
    0.66
     conflictos
    0.63
    abuse
    0.63
    violations
    0.60
    conflict
    0.60
     disruptions
    0.59
     adverse
    0.59
     overfitting
    0.59
    災
    0.58
    Act Density 0.042%

    No Known Activations