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

    Neuronpedia

    INDEX
    Explanations

    code or errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obed
    -0.07
    ίν
    -0.07
     DbType
    -0.06
     busiest
    -0.06
     Afterwards
    -0.06
    )=
    -0.06
     dragged
    -0.06
    ΟΙ
    -0.06
    ]').
    -0.06
    (INVOKE
    -0.06
    POSITIVE LOGITS
     programmers
    0.07
     konk
    0.07
    uns
    0.06
    Think
    0.06
     CString
    0.06
    pps
    0.06
     SLOT
    0.06
    wand
    0.06
     rozh
    0.06
     معل
    0.06
    Act Density 0.000%

    No Known Activations