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
    ymes
    -0.07
    greso
    -0.06
    anon
    -0.06
     قائمة
    -0.06
     {*
    -0.06
     куда
    -0.06
    vw
    -0.06
     nalez
    -0.06
     Tak
    -0.06
    raní
    -0.05
    POSITIVE LOGITS
    worked
    0.07
     exemption
    0.07
     žal
    0.06
    openid
    0.06
     panel
    0.06
    _INCLUDED
    0.06
    ship
    0.06
     genetics
    0.06
     pact
    0.06
     hopefully
    0.06
    Act Density 0.013%

    No Known Activations