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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    閪
    0.45
     accepté
    0.44
    শায়
    0.43
     spriteBatch
    0.43
     accepter
    0.43
    IdleSync
    0.42
    岫
    0.42
    Accepted
    0.40
    啕
    0.40
    ޏ
    0.40
    POSITIVE LOGITS
     Werk
    0.42
      
    0.40
     or
    0.40
    ready
    0.37
    窗
    0.37
     Bisch
    0.37
    let
    0.37
     или
    0.37
     Meteor
    0.37
     men
    0.36
    Act Density 0.000%

    No Known Activations