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

    Neuronpedia

    INDEX
    Explanations

    code and unstructured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gewohnt
    -0.44
     säll
    -0.41
    siez
    -0.40
     nettement
    -0.40
     piernas
    -0.38
    íslu
    -0.38
    ább
    -0.38
    ceau
    -0.38
     delar
    -0.38
     äldre
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.79
     Signalez
    0.68
    WebServlet
    0.66
    StoreMessageInfo
    0.64
    ()])
    0.63
    ])));
    0.63
    mybatisplus
    0.62
    ()]);
    0.61
    numerusform
    0.59
    woof
    0.57
    Act Density 0.000%

    No Known Activations