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

    Neuronpedia

    INDEX
    Explanations

    falsifiability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nr
    -0.06
    精
    -0.06
    调用
    -0.06
     stone
    -0.06
    _href
    -0.06
     المغرب
    -0.06
     精
    -0.06
     внимание
    -0.06
    mond
    -0.06
     pom
    -0.06
    POSITIVE LOGITS
    _reaction
    0.07
     pci
    0.07
    getApplication
    0.06
    ]bool
    0.06
    eyed
    0.06
    _CL
    0.06
    licts
    0.06
     ethnicity
    0.06
    (gca
    0.06
    .parseInt
    0.06
    Act Density 0.000%

    No Known Activations