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

    Neuronpedia

    INDEX
    Explanations

    cricket

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .includes
    -0.07
    友
    -0.07
    izations
    -0.06
     Lanka
    -0.06
     accompagn
    -0.06
     vape
    -0.06
    izable
    -0.06
    ization
    -0.06
    itter
    -0.06
     blind
    -0.06
    POSITIVE LOGITS
    @extends
    0.07
     isEqualToString
    0.07
    @interface
    0.07
     ComponentFixture
    0.06
     sockfd
    0.06
    detach
    0.06
     موجب
    0.06
     элек
    0.06
     роботу
    0.06
    ;left
    0.06
    Act Density 0.004%

    No Known Activations