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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    া�
    -0.06
    óż
    -0.06
     nap
    -0.06
    验证
    -0.06
     �
    -0.06
    .+
    -0.06
     Meg
    -0.06
    ภาพ
    -0.06
    adx
    -0.06
    ^K
    -0.06
    POSITIVE LOGITS
    -access
    0.08
    MatrixMode
    0.07
    igrationBuilder
    0.06
    tips
    0.06
     envelopes
    0.06
    lut
    0.06
    .re
    0.06
     sert
    0.06
    вести
    0.06
    Dispatch
    0.06
    Act Density 0.012%

    No Known Activations