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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pont
    -0.07
    =YES
    -0.07
    Flight
    -0.07
    �
    -0.07
    failed
    -0.07
    [slot
    -0.07
    icate
    -0.06
    	area
    -0.06
    _sites
    -0.06
    recursive
    -0.06
    POSITIVE LOGITS
     Miles
    0.06
     generously
    0.06
     vit
    0.06
     surprisingly
    0.06
     dòng
    0.06
    .,↵
    0.06
    sumer
    0.06
     surprising
    0.06
     同
    0.06
     invoice
    0.06
    Act Density 0.050%

    No Known Activations