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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROP
    -0.27
    ÑĮÑĤе
    -0.26
    logg
    -0.26
     exciting
    -0.25
    etics
    -0.25
    rite
    -0.25
    åŀ©
    -0.25
    è¹ī
    -0.24
    æIJ½
    -0.24
    roud
    -0.24
    POSITIVE LOGITS
    æŧ
    0.31
    éĹŃ
    0.29
    å¥ļ
    0.27
    âĺħ
    0.26
     âĺħ
    0.26
    otta
    0.25
    åij¨åĪĬ
    0.25
    etten
    0.25
    اØ
    0.24
    éĩijåŃĹ
    0.24
    Act Density 0.002%

    No Known Activations