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

    Neuronpedia

    INDEX
    Explanations

    Memory visibility and threading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     발
    -0.07
     screaming
    -0.07
    StringLength
    -0.07
     exc
    -0.07
    .Excel
    -0.07
     TRY
    -0.07
    IDDLE
    -0.07
     любом
    -0.07
     Stadium
    -0.06
    行驶
    -0.06
    POSITIVE LOGITS
    ネ
    0.07
    .Or
    0.07
     preorder
    0.07
    曾任
    0.07
    ┚
    0.07
     ngũ
    0.07
     Polish
    0.07
    ôm
    0.07
    ment
    0.07
    aga
    0.07
    Act Density 0.009%

    No Known Activations