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

    Neuronpedia

    INDEX
    Explanations

    supply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    етод
    -0.07
    >_
    -0.07
    変
    -0.07
    砂
    -0.07
    ⊕
    -0.07
    inea
    -0.07
    "^
    -0.06
    ioxide
    -0.06
    平面
    -0.06
    𬇹
    -0.06
    POSITIVE LOGITS
    .Core
    0.08
    不可或缺
    0.08
     Farmers
    0.07
     informant
    0.07
     berhasil
    0.07
    专注
    0.07
     ASSIGN
    0.07
    adol
    0.07
     RootState
    0.07
    essential
    0.07
    Act Density 0.044%

    No Known Activations