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

    Neuronpedia

    INDEX
    Explanations

    varied text types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anomal
    -0.08
     hogar
    -0.08
    -0.08
     Carm
    -0.08
     resc
    -0.08
     faltar
    -0.08
     códigos
    -0.07
     lifting
    -0.07
     Born
    -0.07
     kod
    -0.07
    POSITIVE LOGITS
    ↵   ↵
    0.09
     ↵  ↵↵
    0.09
    ↵      ↵
    0.08
     philippines
    0.08
    amakuru
    0.08
    ↵            ↵
    0.08
     প্ৰকাশ
    0.08
    រ�
    0.08
    ↵↵ ↵
    0.08
    ↵                    ↵
    0.08
    Act Density 0.351%
    No Known Activations