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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你也
    -0.08
    .getById
    -0.07
    じゃ
    -0.07
    .ITEM
    -0.07
    却
    -0.07
    훗
    -0.07
    isEqual
    -0.07
    如果你
    -0.07
    ştır
    -0.07
    משקיע
    -0.07
    POSITIVE LOGITS
    -court
    0.08
    Writer
    0.07
     hardly
    0.07
    機
    0.07
    _Matrix
    0.07
    羟
    0.07
    .No
    0.06
     إطار
    0.06
    环
    0.06
    pe
    0.06
    Act Density 0.012%

    No Known Activations