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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arrival
    -0.07
     Venue
    -0.06
     компании
    -0.06
    getIndex
    -0.06
     الوز
    -0.06
     сест
    -0.06
    agh
    -0.06
    炮
    -0.06
     pleasure
    -0.06
    Ru
    -0.06
    POSITIVE LOGITS
    yaw
    0.07
     bx
    0.07
    _InitStructure
    0.07
    _iff
    0.07
    oli
    0.07
     Mao
    0.07
     crisp
    0.06
     proposition
    0.06
    �
    0.06
    =X
    0.06
    Act Density 0.036%

    No Known Activations