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

    Neuronpedia

    INDEX
    Explanations

    complexes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uka
    -0.10
     runs
    -0.08
     lorem
    -0.07
    ...↵↵
    -0.07
    kehr
    -0.07
     derives
    -0.07
    fulness
    -0.07
     burn
    -0.07
    stroke
    -0.07
     sleeps
    -0.07
    POSITIVE LOGITS
     ಬಂಧ
    0.13
     adsorption
    0.12
     complexes
    0.11
     seques
    0.10
     আটক
    0.10
     avid
    0.10
     attachments
    0.10
    .binding
    0.09
     partnerships
    0.09
     formando
    0.09
    Act Density 0.016%

    No Known Activations