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

    Neuronpedia

    INDEX
    Explanations

    fa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Leod
    -0.07
     newIndex
    -0.07
     csrf
    -0.06
     empres
    -0.06
     Voy
    -0.06
     Ket
    -0.06
    .account
    -0.06
     colum
    -0.06
    ']=$
    -0.06
    UZ
    -0.06
    POSITIVE LOGITS
    当
    0.07
    ات
    0.07
    ovaná
    0.06
    arnings
    0.06
    _div
    0.06
    vv
    0.06
     subscribe
    0.06
    -man
    0.06
     Man
    0.06
     continually
    0.06
    Act Density 0.001%

    No Known Activations