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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seb
    -0.07
    .Open
    -0.07
     rpc
    -0.06
     Entre
    -0.06
    forth
    -0.06
     sorumlu
    -0.06
    璃
    -0.06
    .localization
    -0.06
    ٬
    -0.06
    乡
    -0.06
    POSITIVE LOGITS
    StringBuilder
    0.08
    juries
    0.07
    Une
    0.07
    ],↵
    0.06
    [];↵
    0.06
     German
    0.06
    abilidad
    0.06
    ORDER
    0.06
     interfaces
    0.06
     ear
    0.06
    Act Density 0.005%

    No Known Activations