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

    Neuronpedia

    INDEX
    Explanations

    Median income

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kits
    -0.07
    统统
    -0.07
    缧
    -0.07
     Magnetic
    -0.07
    :YES
    -0.07
     Mahm
    -0.07
    ardless
    -0.07
    \db
    -0.07
     MainForm
    -0.07
    .after
    -0.07
    POSITIVE LOGITS
                  
↵
    0.08
    "
↵
    0.07
    =""↵
    0.07
     sister
    0.07
    _called
    0.07
    _sem
    0.07
     beginnings
    0.07
    #
    0.07
    entry
    0.07
    "↵
    0.07
    Act Density 0.000%

    No Known Activations