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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    triangle
    -0.07
     стил
    -0.07
     Conversation
    -0.07
    .UseText
    -0.06
     almaktadır
    -0.06
    .are
    -0.06
     roleId
    -0.06
    اطعة
    -0.06
    .Task
    -0.06
     Judge
    -0.06
    POSITIVE LOGITS
    :"↵
    0.06
     conveying
    0.06
    .gson
    0.06
    itted
    0.06
     bowed
    0.06
     पक
    0.06
     fp
    0.06
     finalize
    0.06
    *y
    0.06
    hz
    0.05
    Act Density 0.015%

    No Known Activations