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

    Neuronpedia

    INDEX
    Explanations

    plus sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quý
    -0.07
     tổng
    -0.07
     Vương
    -0.07
    麻辣
    -0.07
     BYTE
    -0.07
    	glBind
    -0.07
     absorbing
    -0.06
     pathological
    -0.06
    מחלה
    -0.06
    营销
    -0.06
    POSITIVE LOGITS
    ⓘ
    0.08
    钵
    0.08
     SCIP
    0.07
    汶
    0.07
    _TREE
    0.07
     Begins
    0.07
     �
    0.07
    平均每
    0.07
    refixer
    0.06
     graffiti
    0.06
    Act Density 0.014%

    No Known Activations