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

    Neuronpedia

    INDEX
    Explanations

    code/structured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tat
    -0.07
    SAME
    -0.07
     deterior
    -0.07
    ])↵↵
    -0.06
    .charAt
    -0.06
    -lfs
    -0.06
     �
    -0.06
    ivamente
    -0.06
     سابق
    -0.06
    。”↵↵
    -0.06
    POSITIVE LOGITS
    ；
    0.06
    olkata
    0.06
    643
    0.06
    ガ
    0.06
    考え
    0.06
    신
    0.06
    �게
    0.06
    <d
    0.06
     metabolic
    0.06
    UD
    0.06
    Act Density 0.003%

    No Known Activations