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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ub
    -0.07
     Benefit
    -0.07
     facility
    -0.07
    ierung
    -0.07
    ุณ
    -0.06
     motive
    -0.06
    arp
    -0.06
     Frankfurt
    -0.06
     staveb
    -0.06
    orthy
    -0.06
    POSITIVE LOGITS
    KT
    0.06
     pprint
    0.06
     xsi
    0.06
    	tests
    0.06
    //
    0.06
    buster
    0.06
    服
    0.06
    _RSP
    0.06
     Strap
    0.06
     스트
    0.06
    Act Density 0.071%

    No Known Activations