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

    Neuronpedia

    INDEX
    Explanations

    Cl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mushroom
    -0.07
     reward
    -0.06
     miners
    -0.06
     missions
    -0.06
    _cu
    -0.06
     missile
    -0.06
     Exped
    -0.06
     мова
    -0.06
     rel
    -0.06
    HashMap
    -0.06
    POSITIVE LOGITS
    .isDefined
    0.07
     urlpatterns
    0.07
    ↵            
↵
    0.07
    Mrs
    0.06
    ูช
    0.06
     companyName
    0.06
    ekl
    0.06
     toàn
    0.06
    灣
    0.06
    Leon
    0.06
    Act Density 0.007%

    No Known Activations