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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    504
    -0.07
    ='%
    -0.07
     richer
    -0.06
    actic
    -0.06
    zure
    -0.06
    公共
    -0.06
     recognizable
    -0.06
    (relative
    -0.06
     Maxwell
    -0.06
     jin
    -0.06
    POSITIVE LOGITS
    �i
    0.07
    header
    0.06
     homosexuality
    0.06
    .gson
    0.06
    earning
    0.06
    .setState
    0.06
     conspiracy
    0.06
    ebi
    0.06
    	sp
    0.06
    kg
    0.06
    Act Density 0.049%

    No Known Activations