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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �新
    -0.07
    _kw
    -0.07
    okud
    -0.07
    理
    -0.07
    older
    -0.06
    ，如果
    -0.06
    Schedulers
    -0.06
    icolon
    -0.06
    stroke
    -0.06
     populace
    -0.06
    POSITIVE LOGITS
    	title
    0.06
    	pass
    0.06
    auc
    0.06
     측
    0.06
     Penn
    0.06
    fort
    0.06
    entiful
    0.06
     lesbienne
    0.06
     Greek
    0.06
     radically
    0.06
    Act Density 0.008%

    No Known Activations