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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +='
    -0.06
    ervoir
    -0.06
     Hospitals
    -0.06
     signed
    -0.06
    336
    -0.06
    :"↵
    -0.06
     DbType
    -0.06
     Job
    -0.06
    734
    -0.05
    创
    -0.05
    POSITIVE LOGITS
    rschein
    0.07
    sil
    0.07
    efined
    0.07
     ecc
    0.07
     Kah
    0.06
     kannst
    0.06
    ิมพ
    0.06
    あ
    0.06
     musel
    0.06
    هر
    0.06
    Act Density 0.013%

    No Known Activations