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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =".$
    -0.07
    所谓
    -0.07
    	block
    -0.07
    汶
    -0.07
    枲
    -0.07
    艺
    -0.07
    *>::
    -0.07
    印
    -0.07
    ∑
    -0.07
    стой
    -0.07
    POSITIVE LOGITS
    usr
    0.08
    信用卡
    0.08
     favorites
    0.07
    ɦ
    0.07
     nrw
    0.07
     продолж
    0.07
     Interpret
    0.07
     Battery
    0.07
     shortened
    0.07
    istorical
    0.07
    Act Density 0.057%

    No Known Activations