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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WHICH
    -0.07
     which
    -0.07
    ])(
    -0.06
    orient
    -0.06
     prest
    -0.06
    '}}
    -0.06
     lr
    -0.06
     //{
    -0.06
     caches
    -0.06
     forming
    -0.06
    POSITIVE LOGITS
    agnetic
    0.06
    ('/');↵
    0.06
    .OK
    0.06
    /DD
    0.06
    ��
    0.06
    “She
    0.06
    fc
    0.06
    bad
    0.06
    ferred
    0.06
    file
    0.06
    Act Density 0.003%

    No Known Activations