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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cháze
    -0.07
    ану
    -0.07
    nahme
    -0.07
    ceptions
    -0.06
    ुलन
    -0.06
    陶
    -0.06
    argout
    -0.06
    chner
    -0.06
     آور
    -0.06
    езда
    -0.06
    POSITIVE LOGITS
     kancel
    0.06
    .ph
    0.06
     ό
    0.06
     wag
    0.06
    菜
    0.06
    」↵↵
    0.06
    abetes
    0.06
    .SelectedValue
    0.06
     Cabin
    0.06
     comic
    0.06
    Act Density 0.016%

    No Known Activations