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

    Neuronpedia

    INDEX
    Explanations

    someone, somebody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Initially
    0.55
     প্রথমে
    0.55
     inicialmente
    0.54
    Initially
    0.53
     initially
    0.53
     intrigued
    0.51
     originally
    0.49
    好奇
    0.49
     zunächst
    0.46
     exploit
    0.45
    POSITIVE LOGITS
    有人
    0.54
    someone
    0.52
     someone
    0.51
    Someone
    0.49
     somebody
    0.48
     jemand
    0.46
     Someone
    0.45
     alguien
    0.45
    Somebody
    0.44
     Somebody
    0.44
    Act Density 0.006%

    No Known Activations