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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    226
    -0.07
    575
    -0.07
    near
    -0.07
    those
    -0.07
    949
    -0.07
     places
    -0.07
     near
    -0.07
     blas
    -0.07
     those
    -0.06
     whatever
    -0.06
    POSITIVE LOGITS
    ].↵
    0.07
    俄
    0.07
    .↵
    0.06
    ]
    0.06
    ).↵
    0.06
     AABB
    0.06
    ().
    0.06
    ẻ
    0.06
     seb
    0.06
    .
    0.06
    Act Density 0.268%

    No Known Activations