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

    Neuronpedia

    INDEX
    Explanations

    DIY instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ingers
    -0.07
    ैज
    -0.07
    cé
    -0.07
    .getStatus
    -0.07
    olk
    -0.07
    `,
    -0.07
    oving
    -0.07
     Buttons
    -0.07
    eling
    -0.07
    CLS
    -0.06
    POSITIVE LOGITS
     Rolling
    0.06
     раст
    0.06
    ระด
    0.06
     feather
    0.06
    ो।
    0.06
    を行
    0.06
     hend
    0.05
    ijkl
    0.05
     yasal
    0.05
    анная
    0.05
    Act Density 0.042%

    No Known Activations