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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .debugLine
    -0.07
     restitution
    -0.07
    thag
    -0.07
     Responsibilities
    -0.07
    쥘
    -0.07
    횡
    -0.06
    背上
    -0.06
    ✺
    -0.06
     rz
    -0.06
     plur
    -0.06
    POSITIVE LOGITS
    Self
    0.08
    課
    0.07
    OP
    0.07
     Kashmir
    0.07
    雪山
    0.07
     Hind
    0.07
    ов
    0.07
    生产线
    0.07
    contained
    0.07
    이라
    0.07
    Act Density 0.008%

    No Known Activations