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

    Neuronpedia

    INDEX
    Explanations

    house

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    感觉自己
    -0.07
    �
    -0.07
     Gord
    -0.07
    加紧
    -0.07
     gains
    -0.07
     exper
    -0.07
    近三年
    -0.07
     xs
    -0.07
     ממש
    -0.07
     async
    -0.07
    POSITIVE LOGITS
    0.08
    onomy
    0.07
    flamm
    0.07
     Hex
    0.07
    .equal
    0.07
    또
    0.06
     OLD
    0.06
    텦
    0.06
    딕
    0.06
    奋斗目标
    0.06
    Act Density 0.001%

    No Known Activations