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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SuppressWarnings
    -0.07
     squid
    -0.07
    Vm
    -0.07
    	select
    -0.07
    之间
    -0.06
     ];
↵
    -0.06
    "]]
    -0.06
     vu
    -0.06
    .next
    -0.06
    _is
    -0.06
    POSITIVE LOGITS
     Carlson
    0.07
    ?
    0.07
    (pad
    0.07
    產
    0.06
     Canadiens
    0.06
    ?!
    0.06
     summar
    0.06
     зокрема
    0.06
     obe
    0.06
     Vienna
    0.06
    Act Density 0.085%

    No Known Activations