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

    Neuronpedia

    INDEX
    Explanations

    As of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     participate
    0.46
     disent
    0.44
     umożliw
    0.43
     özellikle
    0.42
     participates
    0.42
     wykorzyst
    0.41
     participated
    0.40
     esche
    0.40
     באופן
    0.40
     وبر
    0.40
    POSITIVE LOGITS
     much
    0.85
    much
    0.84
    Much
    0.82
     MUCH
    0.75
     far
    0.66
     Much
    0.66
     mucho
    0.64
     mucha
    0.64
     paljon
    0.53
     soon
    0.51
    Act Density 0.138%

    No Known Activations