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

    Neuronpedia

    INDEX
    Explanations

    actions and involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Embrace
    0.41
    orry
    0.40
     degener
    0.40
    ពេលវេល
    0.40
     embrace
    0.39
     evolves
    0.38
    राधना
    0.38
     اهل
    0.38
     estable
    0.37
     embraces
    0.37
    POSITIVE LOGITS
     participated
    1.13
     participate
    1.13
    particip
    1.13
    参加
    1.09
    Particip
    1.07
    参与
    1.06
     assisting
    1.02
     уча
    1.01
     partecipare
    1.00
     participates
    1.00
    Act Density 0.019%

    No Known Activations