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

    Neuronpedia

    INDEX
    Explanations

    picture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¸ĤæķĻèĤ²
    -0.26
     lÃŃ
    -0.26
     Original
    -0.25
    ä¸¤å¼ł
    -0.25
    ä¸Ģè½®
    -0.25
     lame
    -0.25
    PIP
    -0.25
     berlin
    -0.25
    fic
    -0.24
    åİŁ
    -0.24
    POSITIVE LOGITS
    SSION
    0.33
     dissoci
    0.27
    èĥ½åĬĽå¼º
    0.27
     Hurt
    0.26
    edo
    0.25
    dong
    0.24
    aldo
    0.24
     cheated
    0.24
     encodeURIComponent
    0.24
    .ObjectModel
    0.24
    Act Density 0.020%

    No Known Activations