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

    Neuronpedia

    INDEX
    Explanations

    widely recognized, universally considered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otu
    0.42
    $^{-
    0.39
    omyc
    0.39
    getMessage
    0.38
    iego
    0.37
    貌
    0.37
    ave
    0.37
    Aly
    0.37
    getPrice
    0.36
    ▪
    0.36
    POSITIVE LOGITS
     ])
    0.39
     Jaguar
    0.39
     expend
    0.38
     Latina
    0.38
     ESG
    0.38
     TRS
    0.35
    Leg
    0.35
    cloak
    0.35
     Journ
    0.35
     Leg
    0.35
    Act Density 0.003%

    No Known Activations