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

    Neuronpedia

    INDEX
    Explanations

    creative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cor
    -0.28
    èģĶ
    -0.26
    ãģĵ
    -0.26
    elect
    -0.26
    ãģĹãģ°
    -0.25
    ãĥ¥
    -0.25
    emploi
    -0.25
    å¸Ī
    -0.24
    acco
    -0.24
    corr
    -0.24
    POSITIVE LOGITS
     maiden
    0.26
    >Description
    0.25
    stead
    0.25
    ê²IJ
    0.25
    icz
    0.24
     ®
    0.24
    åĨįéĢł
    0.24
    castle
    0.24
    /domain
    0.24
    ä¸ĭ车
    0.24
    Act Density 0.819%

    No Known Activations