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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helpless
    -0.28
    æ§
    -0.26
    麻å°Ĩ
    -0.24
     Achilles
    -0.24
     bindActionCreators
    -0.23
    æļĩ
    -0.23
    çľĭçĶµå½±
    -0.23
    HWND
    -0.23
    .jav
    -0.23
    ificar
    -0.23
    POSITIVE LOGITS
    å¾·æĭī
    0.28
    iox
    0.28
     sources
    0.26
    åijĬ
    0.26
    ÑģÑĤи
    0.26
    éĥ¨
    0.25
    âĦľ
    0.24
    ivalent
    0.24
     scrap
    0.24
    arts
    0.24
    Act Density 0.052%

    No Known Activations