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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĪªæŃ¢
    -0.30
    à¤ij
    -0.28
    ollapsed
    -0.26
    ä¸Ģèĩ´æĢ§
    -0.24
    ÑĢай
    -0.24
    巴士
    -0.24
     deck
    -0.24
    GLE
    -0.24
    met
    -0.23
     ling
    -0.23
    POSITIVE LOGITS
    apore
    0.29
    éĩįè¦ģåĨħ容
    0.28
    ÄĻd
    0.27
    æī¿æĭħ责任
    0.27
    å½¹
    0.26
    ÃŃlia
    0.26
    ero
    0.26
    ERO
    0.25
    OMATIC
    0.25
    erÃł
    0.24
    Act Density 0.320%

    No Known Activations