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

    Neuronpedia

    INDEX
    Explanations

    metro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addock
    -0.07
    ບ
    -0.07
    andle
    -0.07
    ید
    -0.07
     Ald
    -0.07
     anecd
    -0.07
    .Code
    -0.07
    Overview
    -0.07
     envelope
    -0.07
    ordial
    -0.07
    POSITIVE LOGITS
     paternal
    0.08
     остальн
    0.08
    рем
    0.07
    𬳽
    0.07
     équip
    0.07
    פיצוי
    0.07
    深加工
    0.07
     ruthless
    0.07
    إخ
    0.07
    )didReceiveMemoryWarning
    0.07
    Act Density 0.003%

    No Known Activations