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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ahụ
    -0.09
     tähän
    -0.09
    سكري
    -0.09
    منٹ
    -0.09
    ындағы
    -0.09
     વગેરે
    -0.09
     bavuga
    -0.08
     këtë
    -0.08
     permainan
    -0.08
     coveted
    -0.08
    POSITIVE LOGITS
     immediate
    0.10
     right
    0.10
    Immediate
    0.09
    right
    0.09
     left
    0.08
     오른
    0.08
     الجانب
    0.08
     rights
    0.08
     direita
    0.08
    ia
    0.08
    Act Density 0.020%

    No Known Activations