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

    Neuronpedia

    INDEX
    Explanations

    virus variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ロール
    0.36
    lee
    0.36
    ué
    0.36
     ನೋಡ
    0.34
    we
    0.34
    री
    0.34
     deducting
    0.34
    べ
    0.34
    Indic
    0.33
    âne
    0.33
    POSITIVE LOGITS
     virus
    0.56
     Virus
    0.55
     prov
    0.48
     Prov
    0.46
    Virus
    0.46
     वायरस
    0.45
     прово
    0.42
    病毒
    0.42
     Stairs
    0.42
     ভাইরাস
    0.42
    Act Density 0.000%

    No Known Activations