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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cz
    -0.07
    	out
    -0.07
    Career
    -0.06
    -vs
    -0.06
     usuarios
    -0.06
    uali
    -0.06
    ListModel
    -0.06
     Sto
    -0.06
    �y
    -0.06
    ूं
    -0.06
    POSITIVE LOGITS
     Prophet
    0.07
     reclaim
    0.07
     eclipse
    0.06
     Homeland
    0.06
     proposition
    0.06
    設定
    0.06
     numerator
    0.06
    _ANT
    0.06
     redirection
    0.06
    едак
    0.06
    Act Density 0.011%

    No Known Activations