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

    Neuronpedia

    INDEX
    Explanations

    minute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avage
    -0.28
    åĪĩ
    -0.27
    oll
    -0.27
    oseconds
    -0.27
    gorithm
    -0.26
    ög
    -0.25
    åħĭ
    -0.25
     divisions
    -0.25
    extends
    -0.24
    龸
    -0.24
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.27
    çĪ¬
    0.26
    esus
    0.26
    踱
    0.26
    éķ¿éĢĶ
    0.25
    "--
    0.25
     Map
    0.25
    ingle
    0.25
    ç»ĵæŀĦè°ĥæķ´
    0.24
    nze
    0.24
    Act Density 0.003%

    No Known Activations