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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -important
    -0.07
    Und
    -0.07
     pictured
    -0.07
     grieving
    -0.07
    _invoke
    -0.06
    _regex
    -0.06
    Hand
    -0.06
    >$
    -0.06
    .Pos
    -0.06
     美国
    -0.06
    POSITIVE LOGITS
    รรค
    0.06
    recur
    0.06
     ;↵↵↵
    0.06
     createdAt
    0.06
     ↵↵↵↵↵
    0.06
     clearInterval
    0.06
    VES
    0.06
    pcm
    0.06
    ONTAL
    0.06
    	queue
    0.05
    Act Density 0.076%

    No Known Activations