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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vý
    -0.07
    tx
    -0.06
     critique
    -0.06
    Lambda
    -0.06
     membranes
    -0.06
    volt
    -0.06
    styles
    -0.06
    721
    -0.06
    /contact
    -0.06
     feats
    -0.06
    POSITIVE LOGITS
     must
    0.08
    部门
    0.07
     días
    0.07
    ість
    0.07
    incerely
    0.07
     Unblock
    0.06
     enlarge
    0.06
    Goal
    0.06
     NAT
    0.06
     Bian
    0.06
    Act Density 0.022%

    No Known Activations