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

    Neuronpedia

    INDEX
    Explanations

    need for action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tex
    -0.08
     partie
    -0.07
     alone
    -0.06
    eceğiz
    -0.06
     BEFORE
    -0.06
     všichni
    -0.06
    Firestore
    -0.06
     makes
    -0.06
     unnoticed
    -0.06
    "Yes
    -0.06
    POSITIVE LOGITS
    ร
    0.07
     freely
    0.06
     india
    0.06
    Term
    0.06
    ,strlen
    0.06
     Senior
    0.06
    acyj
    0.06
    compiler
    0.06
    	bg
    0.06
     النو
    0.05
    Act Density 0.080%

    No Known Activations