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
     động
    -0.07
    	form
    -0.06
    営
    -0.06
     tents
    -0.06
     cursos
    -0.06
    たく
    -0.06
    нувся
    -0.06
     "&
    -0.06
    851
    -0.06
    ());
↵
    -0.06
    POSITIVE LOGITS
    Exports
    0.07
    _java
    0.06
    .process
    0.06
     حتى
    0.06
    .:.:.:.:
    0.06
     Další
    0.06
     нав
    0.06
    ุย
    0.06
    �
    0.06
    ительность
    0.06
    Act Density 0.001%

    No Known Activations