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

    Neuronpedia

    INDEX
    Explanations

    .data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跑步
    -0.07
     mMap
    -0.07
    (INVOKE
    -0.07
     Mỗi
    -0.07
    犹如
    -0.07
    著名
    -0.07
    (word
    -0.07
     accompanying
    -0.07
     espec
    -0.07
    首次
    -0.07
    POSITIVE LOGITS
     Tubes
    0.07
    ROUGH
    0.07
    \Contracts
    0.07
    ire
    0.06
     cis
    0.06
    _DIALOG
    0.06
    .eclipse
    0.06
     потреб
    0.06
     forward
    0.06
    觑
    0.06
    Act Density 0.001%

    No Known Activations