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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Peek
    -0.07
     animal
    -0.06
    /span
    -0.06
    �
    -0.06
     fleece
    -0.06
    にお
    -0.06
     Core
    -0.06
     isOpen
    -0.06
     παιδ
    -0.06
     crud
    -0.06
    POSITIVE LOGITS
    RYPT
    0.07
    arrass
    0.07
     Files
    0.06
    -archive
    0.06
    imestamp
    0.06
    史
    0.06
     files
    0.06
    Emp
    0.06
    yclopedia
    0.06
    renc
    0.06
    Act Density 0.029%

    No Known Activations