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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulti
    -0.07
     gelen
    -0.07
    _skin
    -0.06
     seemed
    -0.06
    328
    -0.06
     waren
    -0.06
     worlds
    -0.06
     schemes
    -0.06
     hieronta
    -0.06
     dinh
    -0.06
    POSITIVE LOGITS
     ἐ
    0.07
     Valle
    0.06
    %timeout
    0.06
    >xpath
    0.06
     Nach
    0.06
     />,↵
    0.06
    _ALWAYS
    0.06
    обходим
    0.06
     прип
    0.06
    еви
    0.06
    Act Density 0.000%

    No Known Activations