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

    Neuronpedia

    INDEX
    Explanations

    average tendency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    แมนเชสเตอร์ซิตี
    0.43
     poise
    0.40
     Maturity
    0.39
    픔
    0.39
    没有人
    0.39
    ђу
    0.38
     че
    0.38
     mesmerizing
    0.38
     जिनको
    0.37
     statistics
    0.37
    POSITIVE LOGITS
     broadly
    0.48
    generally
    0.44
    Generic
    0.43
     generically
    0.43
    Generally
    0.42
     unambiguously
    0.42
     generally
    0.41
     uns
    0.41
     ~$
    0.40
    0.40
    Act Density 0.001%

    No Known Activations