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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cap
    -0.07
    मक
    -0.07
    hand
    -0.07
    _kwargs
    -0.06
     Mild
    -0.06
    onda
    -0.06
    (W
    -0.06
    _xyz
    -0.06
    (ic
    -0.06
    Meg
    -0.06
    POSITIVE LOGITS
    hone
    0.07
    ={[↵
    0.06
    ={},
    0.06
    _UClass
    0.06
    ské
    0.06
     Existing
    0.06
     recession
    0.06
     more
    0.06
     Marino
    0.06
    umm
    0.06
    Act Density 0.031%

    No Known Activations