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

    Neuronpedia

    INDEX
    Explanations

    specifically

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caregiver
    -0.06
    dress
    -0.06
    Skip
    -0.06
    ?,
    -0.06
    sorry
    -0.06
    ورية
    -0.06
    (mapStateToProps
    -0.06
     weekend
    -0.06
    +f
    -0.06
    中央
    -0.06
    POSITIVE LOGITS
     specifically
    0.07
     mile
    0.06
    _DISPATCH
    0.06
    iev
    0.06
     demonstrate
    0.06
    typ
    0.06
    ASURE
    0.06
    shima
    0.06
     Vinci
    0.06
    =========
    0.06
    Act Density 0.031%

    No Known Activations