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

    Neuronpedia

    INDEX
    Explanations

    Aqu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ş
    -0.07
    ман
    -0.07
    ,No
    -0.07
     Merlin
    -0.07
     shred
    -0.07
     �
    -0.07
     CD
    -0.07
     Hide
    -0.06
     HID
    -0.06
     Miles
    -0.06
    POSITIVE LOGITS
     Aqu
    0.12
     aqu
    0.10
    Aqu
    0.10
     aquatic
    0.08
     Aqua
    0.08
     Aquarium
    0.08
    qu
    0.07
     Kitchen
    0.07
    aci
    0.07
    aqu
    0.07
    Act Density 0.018%

    No Known Activations