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

    Neuronpedia

    INDEX
    Explanations

    words related to political debate and business/government controversy

    oai_token-act-pair · gemini-2.0-flash

    Opposition/disagreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelves
    -0.79
     متعلقه
    -0.76
    tagHelperRunner
    -0.75
    ſelf
    -0.75
     linkovi
    -0.74
     surla
    -0.72
     تضيفلها
    -0.72
    Tikang
    -0.71
     ſte
    -0.69
     iſt
    -0.68
    POSITIVE LOGITS
     anti
    0.63
     pro
    0.62
     against
    0.60
     przeciw
    0.59
     counter
    0.59
     opposition
    0.58
     op
    0.55
     prieš
    0.54
    против
    0.54
     opposing
    0.53
    Act Density 2.885%

    No Known Activations