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

    Neuronpedia

    INDEX
    Explanations

    Weekly news summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    核酸
    -0.07
     Collective
    -0.07
     Outreach
    -0.07
     liberation
    -0.07
    ]<
    -0.07
     취
    -0.07
    閉
    -0.07
     AAC
    -0.07
    💣
    -0.07
     lookahead
    -0.07
    POSITIVE LOGITS
    		↵		↵
    0.07
    arya
    0.07
     ventana
    0.07
    弯
    0.07
    ską
    0.07
     وما
    0.07
     finger
    0.07
     screw
    0.06
    (doc
    0.06
     Denis
    0.06
    Act Density 0.033%

    No Known Activations