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

    Neuronpedia

    INDEX
    Explanations

    specific entities or markup

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Planets
    0.58
     MongoClient
    0.54
    职工
    0.54
     Obs
    0.52
     autó
    0.52
     fraî
    0.51
     হবি
    0.51
    Obs
    0.50
     წარ
    0.50
     planète
    0.50
    POSITIVE LOGITS
    btree
    0.66
     triangulation
    0.64
    berry
    0.61
     wijze
    0.61
    umas
    0.60
     условий
    0.60
    topology
    0.60
    vent
    0.60
     शुक्ल
    0.60
    ventil
    0.59
    Act Density 0.001%

    No Known Activations