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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luk
    -0.07
     Disk
    -0.07
     enfermed
    -0.06
    ัก
    -0.06
    begin
    -0.06
    -foot
    -0.06
    273
    -0.06
    interpret
    -0.06
    ב
    -0.06
     plat
    -0.06
    POSITIVE LOGITS
    (Collections
    0.07
    Gas
    0.07
    路径
    0.07
    .ForEach
    0.06
     mdl
    0.06
     μπορού
    0.06
    فته
    0.06
     ί
    0.06
    ног
    0.06
    [item
    0.06
    Act Density 0.073%

    No Known Activations