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

    Neuronpedia

    INDEX
    Explanations

    false statements or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CallOptions
    0.40
     creatividad
    0.39
     юк
    0.38
     кух
    0.37
    条款
    0.37
     chúc
    0.37
    (//
    0.37
     comentado
    0.36
     unresolved
    0.35
    看不到
    0.35
    POSITIVE LOGITS
     positives
    0.74
     representation
    0.64
     portrayal
    0.60
     premise
    0.58
     portray
    0.56
     representations
    0.55
     statements
    0.54
     premises
    0.53
    hood
    0.52
     alarms
    0.52
    Act Density 0.058%

    No Known Activations