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
    switch
    -0.07
    인지
    -0.06
     поперед
    -0.06
     texto
    -0.06
    deleted
    -0.06
    其实
    -0.06
     Hernandez
    -0.06
    HasForeignKey
    -0.06
    两
    -0.06
     weitere
    -0.06
    POSITIVE LOGITS
    代
    0.07
    健
    0.06
    igest
    0.06
     الاع
    0.06
    .df
    0.06
    ]';↵
    0.06
    _NEXT
    0.06
    大学
    0.06
     Rt
    0.06
     toen
    0.06
    Act Density 0.005%

    No Known Activations