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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地理位置
    -0.07
    магаз
    -0.07
    sections
    -0.07
     purchasing
    -0.07
     mood
    -0.07
     sunglasses
    -0.07
    イメージ
    -0.07
    iations
    -0.07
    schemas
    -0.07
    igg
    -0.07
    POSITIVE LOGITS
    }>↵
    0.08
    );}↵
    0.08
    /location
    0.07
    >()->
    0.07
    ')");↵
    0.07
     upheld
    0.07
    ();++
    0.07
    طم
    0.07
     []
↵
    0.07
    ]},↵
    0.07
    Act Density 0.033%

    No Known Activations