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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ARG
    -0.07
     BIT
    -0.07
    _VALIDATE
    -0.07
    ERV
    -0.06
    рест
    -0.06
     pathology
    -0.06
     profes
    -0.06
    	make
    -0.06
    ตะว
    -0.06
    POSITIVE LOGITS
    "'↵
    0.07
    (ec
    0.07
    (log
    0.07
    Oracle
    0.06
     Oracle
    0.06
     Vie
    0.06
     electric
    0.06
    rico
    0.06
    Enjoy
    0.06
     skyline
    0.06
    Act Density 0.003%

    No Known Activations