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

    Neuronpedia

    INDEX
    Explanations

    code, debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staveb
    -0.06
    hci
    -0.06
     tặng
    -0.06
     fo
    -0.06
     xin
    -0.06
     colonial
    -0.06
     praised
    -0.06
    Fat
    -0.06
     Terrain
    -0.06
    lij
    -0.06
    POSITIVE LOGITS
     affiliate
    0.07
    MHz
    0.07
    (errno
    0.07
     vás
    0.07
    second
    0.07
    baby
    0.07
     clinic
    0.07
     obey
    0.06
     useForm
    0.06
    浦
    0.06
    Act Density 0.001%

    No Known Activations