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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    烟草
    -0.08
    啕
    -0.08
     בשנת
    -0.07
     IEntity
    -0.07
    Requirements
    -0.07
    itzerland
    -0.07
    מטוס
    -0.07
     dừng
    -0.07
    휭
    -0.06
     Desmond
    -0.06
    POSITIVE LOGITS
     hopeless
    0.06
     appended
    0.06
    multi
    0.06
     Website
    0.06
     PUT
    0.06
     wrap
    0.06
    ,number
    0.06
     constant
    0.06
    サロン
    0.06
    alker
    0.06
    Act Density 0.001%

    No Known Activations