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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agricult
    -0.07
    ровер
    -0.07
     زمان
    -0.07
     Reaction
    -0.07
    γι
    -0.07
    arden
    -0.07
     방법
    -0.07
    られ
    -0.07
     palabra
    -0.07
    ख
    -0.06
    POSITIVE LOGITS
    해요
    0.06
     embodied
    0.06
     México
    0.06
    CheckBox
    0.06
    .Generated
    0.06
     repell
    0.06
    0.05
    _triggered
    0.05
    -ed
    0.05
    _membership
    0.05
    Act Density 0.033%

    No Known Activations