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

    Neuronpedia

    INDEX
    Explanations

    advice, warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jal
    -0.08
     Thực
    -0.08
    odega
    -0.08
    bucks
    -0.08
     trivia
    -0.07
    .rmi
    -0.07
     Datagram
    -0.06
     television
    -0.06
    ᒪ
    -0.06
    _store
    -0.06
    POSITIVE LOGITS
    computer
    0.07
    )}↵↵
    0.07
    超级
    0.07
    ，↵
    0.06
    flows
    0.06
    (serializers
    0.06
    胣
    0.06
     strengthens
    0.06
     veröffentlicht
    0.06
    })}↵
    0.06
    Act Density 0.097%

    No Known Activations