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

    Neuronpedia

    INDEX
    Explanations

    talk about, talk in, talk to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rs
    0.59
    ों
    0.58
    ként
    0.57
     Bed
    0.55
    ación
    0.55
    rd
    0.53
     जानकर
    0.53
    ELL
    0.52
    ras
    0.52
    ierung
    0.50
    POSITIVE LOGITS
     tentang
    0.93
     عنها
    0.89
     about
    0.85
    Talking
    0.83
     apie
    0.82
    Talk
    0.79
     عنه
    0.79
     talking
    0.79
     conversar
    0.77
    谈
    0.75
    Act Density 0.072%

    No Known Activations