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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่าร
    -0.07
    >R
    -0.06
    angers
    -0.06
    ilia
    -0.06
    AZY
    -0.06
    ér
    -0.06
    	direction
    -0.06
    .links
    -0.06
    winter
    -0.06
    andelier
    -0.06
    POSITIVE LOGITS
     Sele
    0.07
    .sess
    0.07
     علم
    0.07
     эт
    0.06
    _ALREADY
    0.06
    妈
    0.06
     roleName
    0.06
    .STATUS
    0.06
    іст
    0.06
     procent
    0.06
    Act Density 0.082%

    No Known Activations