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

    Neuronpedia

    INDEX
    Explanations

    (function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌آ
    -0.07
    gateway
    -0.07
    	attack
    -0.06
    Allen
    -0.06
     Alice
    -0.06
    quire
    -0.06
    她们
    -0.06
     вла
    -0.06
     traction
    -0.06
    	include
    -0.06
    POSITIVE LOGITS
    ám
    0.07
     Kin
    0.07
     fl
    0.07
    -graph
    0.07
    .rules
    0.07
     ContentValues
    0.07
    eref
    0.06
     LOCK
    0.06
    /************************************************
    0.06
    Nic
    0.06
    Act Density 0.004%

    No Known Activations