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

    Neuronpedia

    INDEX
    Explanations

    negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     价格
    -0.07
     oils
    -0.07
     Pt
    -0.07
    件
    -0.07
     sperm
    -0.07
     Kenneth
    -0.07
    August
    -0.07
     Version
    -0.06
     Sidebar
    -0.06
    _geo
    -0.06
    POSITIVE LOGITS
     Replacement
    0.07
    .seek
    0.06
    ленных
    0.06
     ]);↵↵
    0.06
    ково
    0.06
     Genuine
    0.06
     hned
    0.06
    ованих
    0.06
     нарез
    0.06
     roční
    0.06
    Act Density 0.114%

    No Known Activations