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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิม
    -0.07
     rec
    -0.07
     painful
    -0.07
    (INPUT
    -0.06
     Mills
    -0.06
    _'
    -0.06
    ENCY
    -0.06
     Sheikh
    -0.06
     mort
    -0.06
     +"
    -0.06
    POSITIVE LOGITS
     differences
    0.06
    Anywhere
    0.06
     vriend
    0.06
     работу
    0.06
     selections
    0.06
     browsing
    0.06
     chance
    0.06
     trade
    0.06
     Lease
    0.06
     skutečnosti
    0.06
    Act Density 0.018%

    No Known Activations