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

    Neuronpedia

    INDEX
    Explanations

    DC movies and actors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    159
    -0.07
     beds
    -0.07
    Crime
    -0.07
     statutory
    -0.07
     Polic
    -0.06
     SCT
    -0.06
     Soup
    -0.06
    soft
    -0.06
    ода
    -0.06
    úmero
    -0.06
    POSITIVE LOGITS
    メラ
    0.07
     Rotate
    0.06
     abras
    0.06
    Photon
    0.06
     removeFrom
    0.06
    '],$_
    0.06
    یف
    0.06
    _templates
    0.06
     jewel
    0.05
     handleError
    0.05
    Act Density 0.008%

    No Known Activations