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

    Neuronpedia

    INDEX
    Explanations

    voice assistants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _purchase
    -0.07
    始
    -0.07
     Lod
    -0.06
    	sp
    -0.06
     repetition
    -0.06
    Thickness
    -0.06
    tement
    -0.06
    licas
    -0.06
    _verify
    -0.06
    )));↵↵
    -0.06
    POSITIVE LOGITS
    180
    0.07
     Characters
    0.07
    .shutdown
    0.06
     &
    0.06
    Inject
    0.06
     đánh
    0.06
    }&
    0.06
    &a
    0.06
    ną
    0.06
     olmadığı
    0.06
    Act Density 0.105%

    No Known Activations