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

    Neuronpedia

    INDEX
    Explanations

    transfer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \M
    -0.07
    �
    -0.07
     PARAM
    -0.07
    寒
    -0.07
    descricao
    -0.07
    办公
    -0.07
     ד
    -0.06
     구
    -0.06
     ม
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     transfer
    0.09
     stripping
    0.08
     transfers
    0.07
    一眼
    0.07
    Don
    0.07
     transferred
    0.07
     trg
    0.07
     transferring
    0.07
    PFN
    0.07
    Neighbors
    0.07
    Act Density 0.022%

    No Known Activations