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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بدء
    -0.07
    ugar
    -0.07
     suction
    -0.06
    (ws
    -0.06
     Large
    -0.06
    -full
    -0.06
    (agent
    -0.06
     mAuth
    -0.06
    <TextView
    -0.06
     LETTER
    -0.06
    POSITIVE LOGITS
    يرا
    0.07
    оборот
    0.07
    앉
    0.07
    .drop
    0.07
    يلي
    0.07
     readable
    0.07
    솊
    0.07
    .emptyList
    0.07
    addField
    0.07
    ዮ
    0.06
    Act Density 0.042%

    No Known Activations