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

    Neuronpedia

    INDEX
    Explanations

    Technical language or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寮
    -0.08
    (Arrays
    -0.07
     작성
    -0.07
     entities
    -0.07
     domic
    -0.06
     CreateMap
    -0.06
     observes
    -0.06
     оборуд
    -0.06
    镭
    -0.06
     applaud
    -0.06
    POSITIVE LOGITS
     picked
    0.07
     wedding
    0.07
     FAMILY
    0.06
    OCKET
    0.06
    female
    0.06
    (bottom
    0.06
    _shader
    0.06
    )}}"
    0.06
     freezer
    0.06
    em
    0.06
    Act Density 0.001%

    No Known Activations