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

    Neuronpedia

    INDEX
    Explanations

    well-formatted text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εται
    -0.07
     ub
    -0.07
    UBE
    -0.06
    Evento
    -0.06
     đị
    -0.06
    лись
    -0.06
                            
↵
    -0.06
    _PAYMENT
    -0.06
    メラ
    -0.06
    нений
    -0.06
    POSITIVE LOGITS
     Winter
    0.07
     applaud
    0.07
     acknowledge
    0.06
     rebuilding
    0.06
     matches
    0.06
     governing
    0.06
    	HANDLE
    0.06
     prayer
    0.06
    Subset
    0.06
     hy
    0.06
    Act Density 0.000%

    No Known Activations