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

    Neuronpedia

    INDEX
    Explanations

    connection between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ехал
    0.41
    电话
    0.41
     Cleanup
    0.41
     Hosting
    0.40
     Coaching
    0.40
     Tuition
    0.40
     Architects
    0.39
     Referee
    0.39
     Corral
    0.39
     Sunglasses
    0.38
    POSITIVE LOGITS
     workable
    0.39
     conjunta
    0.39
     metamorphosis
    0.38
    locked
    0.37
    㚣
    0.37
     Ist
    0.37
     secretos
    0.37
     annen
    0.37
     malle
    0.36
     transferable
    0.36
    Act Density 0.001%

    No Known Activations