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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𦙶
    -0.07
    中外
    -0.07
     inorder
    -0.07
     понрави
    -0.06
    Literal
    -0.06
    .gson
    -0.06
    ขอ
    -0.06
     Allen
    -0.06
    שמר
    -0.06
     MutableList
    -0.06
    POSITIVE LOGITS
    💸
    0.09
    ط
    0.08
    COD
    0.07
     emanc
    0.07
     destinations
    0.07
     posit
    0.07
    cad
    0.07
    네
    0.07
    ķ
    0.07
    -cart
    0.07
    Act Density 0.063%

    No Known Activations