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

    Neuronpedia

    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Elite
    -0.07
    )$_
    -0.06
    .Sub
    -0.06
    utron
    -0.06
    			↵			↵
    -0.06
    divider
    -0.06
     proti
    -0.06
    โค
    -0.06
    coni
    -0.06
    他的
    -0.06
    POSITIVE LOGITS
     purpose
    0.07
     like
    0.06
     fashion
    0.06
    ца
    0.06
     Conduct
    0.06
    ˆ
    0.06
     shell
    0.06
    clusions
    0.06
     Trade
    0.06
    rcode
    0.06
    Act Density 0.434%

    No Known Activations