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
     ik
    -0.06
     Commons
    -0.06
     �
    -0.06
    神
    -0.06
     loaded
    -0.06
     owl
    -0.06
    _sale
    -0.06
     sn
    -0.06
    lng
    -0.05
    _bt
    -0.05
    POSITIVE LOGITS
    ardown
    0.07
    映画
    0.06
     thems
    0.06
    .ps
    0.06
    �nh
    0.06
    //--------------------------------------------------------------↵
    0.06
    STRUCT
    0.06
    #----------------------------------------------------------------
    0.06
    ิตย
    0.06
    -Ch
    0.06
    Act Density 0.001%

    No Known Activations