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

    Neuronpedia

    INDEX
    Explanations

    previously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     French
    -0.09
    },{
    -0.09
     fists
    -0.08
     الفرنسية
    -0.08
    heds
    -0.08
    }_
    -0.08
     sức
    -0.08
    }_{
    -0.07
    French
    -0.07
     العالية
    -0.07
    POSITIVE LOGITS
    已有
    0.12
     предыдущ
    0.10
     προηγ
    0.10
     이전
    0.10
     sebelumnya
    0.09
     eerder
    0.09
     eerdere
    0.09
    已经
    0.09
     anteriores
    0.09
    已
    0.09
    Act Density 0.022%

    No Known Activations