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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    append
    -0.07
    Sigma
    -0.07
    (prefix
    -0.07
    	bytes
    -0.06
    etten
    -0.06
    Closure
    -0.06
    (((
    -0.06
    	lock
    -0.06
    (Chat
    -0.06
    commands
    -0.06
    POSITIVE LOGITS
     TASK
    0.07
     Royal
    0.06
    .jackson
    0.06
     Increased
    0.06
     disagreed
    0.06
     comunic
    0.06
     mid
    0.06
     usual
    0.06
     royal
    0.06
    -г
    0.06
    Act Density 0.070%

    No Known Activations