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

    Neuronpedia

    INDEX
    Explanations

    domain restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /generated
    -0.08
    ummi
    -0.08
    Fat
    -0.08
     Evr
    -0.07
     stk
    -0.07
    etlen
    -0.07
    Pens
    -0.07
     konzent
    -0.07
     AFL
    -0.07
     Chest
    -0.07
    POSITIVE LOGITS
     není
    0.09
     بأنه
    0.08
    ుతో
    0.08
    เป็น
    0.08
     হচ্ছে
    0.08
     readable
    0.07
     оста
    0.07
     ub
    0.07
     becoming
    0.07
    不能为空
    0.07
    Act Density 0.062%

    No Known Activations