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

    Neuronpedia

    INDEX
    Explanations

    Removing parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =password
    -0.06
    unity
    -0.06
     찾아
    -0.06
    戒
    -0.06
    付け
    -0.06
    implement
    -0.06
    _ap
    -0.06
    anyl
    -0.05
    pygame
    -0.05
     باست
    -0.05
    POSITIVE LOGITS
     Elliot
    0.06
     Holmes
    0.06
    SCR
    0.06
     clos
    0.06
     UIAlert
    0.06
     assignable
    0.06
    <::
    0.06
     winds
    0.06
     Traffic
    0.06
     않는
    0.06
    Act Density 0.140%

    No Known Activations