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

    Neuronpedia

    INDEX
    Explanations

    code, files, and computer instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dean
    -0.07
     زنان
    -0.07
    (UINT
    -0.07
     док
    -0.07
    多
    -0.07
     Scotch
    -0.07
     того
    -0.06
    skb
    -0.06
     dvd
    -0.06
    odka
    -0.06
    POSITIVE LOGITS
     nutshell
    0.06
     Carr
    0.06
    compress
    0.06
     ModelRenderer
    0.06
    �
    0.06
     �
    0.06
    Implement
    0.06
    ierge
    0.06
    โจ
    0.06
    lug
    0.06
    Act Density 0.120%

    No Known Activations