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

    Neuronpedia

    INDEX
    Explanations

    gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нести
    -0.06
    (found
    -0.06
    费
    -0.06
     має
    -0.06
     Millennials
    -0.06
     astounding
    -0.06
    .blue
    -0.05
    .headers
    -0.05
    .hwp
    -0.05
    [w
    -0.05
    POSITIVE LOGITS
    acak
    0.07
    Such
    0.07
    uite
    0.07
     Such
    0.07
    (node
    0.07
     централь
    0.06
     fined
    0.06
    ning
    0.06
     exemption
    0.06
     slammed
    0.06
    Act Density 0.040%

    No Known Activations