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

    Neuronpedia

    INDEX
    Explanations

    proud of accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.61
     groaned
    0.58
    뵙
    0.53
    elace
    0.52
     pretends
    0.51
    8
    0.50
    pyrimidine
    0.49
    用の
    0.49
    intendent
    0.49
    ল
    0.48
    POSITIVE LOGITS
    acterial
    0.59
    Proud
    0.58
     ludzie
    0.56
     proud
    0.55
    antaranya
    0.55
     stö
    0.55
     kohta
    0.55
    ingen
    0.54
     vad
    0.54
     ambientes
    0.54
    Act Density 0.004%

    No Known Activations