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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pick
    -0.09
     Semana
    -0.08
     japones
    -0.08
     seguito
    -0.07
    -layer
    -0.07
     hochwertigen
    -0.07
    hmen
    -0.07
    LONG
    -0.07
    but
    -0.07
     उम
    -0.07
    POSITIVE LOGITS
    ஆ
    0.09
     Administrative
    0.08
     Vì
    0.08
     =)
    0.07
     vài
    0.07
     ])
    0.07
     зав
    0.07
     //↵//
    0.07
    ुद
    0.07
     необходимости
    0.07
    Act Density 0.155%

    No Known Activations