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

    Neuronpedia

    INDEX
    Explanations

    components or versions of things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dg
    -0.07
     Trotsky
    -0.07
     саме
    -0.07
     Numero
    -0.07
    Displays
    -0.07
    cmb
    -0.07
     LES
    -0.07
    Alice
    -0.07
    诚
    -0.07
     MessageType
    -0.07
    POSITIVE LOGITS
    nh
    0.06
    	world
    0.06
    estation
    0.06
    ®
    0.06
    िन
    0.06
     họa
    0.06
    _require
    0.06
    нии
    0.06
    [J
    0.06
    หลวง
    0.05
    Act Density 1.560%

    No Known Activations