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

    Neuronpedia

    INDEX
    Explanations

    sensitive subject or topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    är
    0.59
    ör
    0.57
    ，”
    0.51
    ੌਰ
    0.51
    inus
    0.50
    to
    0.49
     a
    0.49
    werk
    0.49
     जु
    0.48
     separating
    0.46
    POSITIVE LOGITS
     Mention
    0.60
    t
    0.59
     konusu
    0.58
    нал
    0.57
    вата
    0.56
     konular
    0.56
     Gladiator
    0.55
    dR
    0.55
    獒
    0.55
     Discuss
    0.54
    Act Density 0.042%

    No Known Activations