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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ただ
    -0.07
    EO
    -0.07
    _LOGIN
    -0.07
    看見
    -0.07
    _FILE
    -0.07
     juice
    -0.06
    现金
    -0.06
    Produces
    -0.06
     coins
    -0.06
    iem
    -0.06
    POSITIVE LOGITS
     Arlington
    0.08
    Fmt
    0.08
    .Google
    0.07
     merged
    0.07
     addTarget
    0.07
     comedic
    0.07
    믾
    0.07
    /sidebar
    0.07
    óm
    0.07
     équip
    0.07
    Act Density 0.371%

    No Known Activations