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

    Neuronpedia

    INDEX
    Explanations

    closely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Action
    -0.08
    体彩
    -0.07
     Foundation
    -0.07
    看电视
    -0.07
    播种
    -0.07
    (images
    -0.06
    ActivityResult
    -0.06
     ViewState
    -0.06
    .junit
    -0.06
    .tagName
    -0.06
    POSITIVE LOGITS
     jogador
    0.08
     shemale
    0.07
    ilor
    0.07
    驳
    0.07
     hacking
    0.07
    ☯
    0.07
     comunic
    0.06
     Owen
    0.06
    훑
    0.06
     Wal
    0.06
    Act Density 0.010%

    No Known Activations