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

    Neuronpedia

    INDEX
    Explanations

    i am writing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capable
    0.57
     confident
    0.53
     capaz
    0.51
     capables
    0.50
     able
    0.49
    confident
    0.48
    Capable
    0.46
    capable
    0.46
     уверен
    0.43
     incapable
    0.43
    POSITIVE LOGITS
     obsession
    0.55
     contacting
    0.49
     so
    0.48
     messaging
    0.46
     emailing
    0.43
    messaging
    0.43
     SO
    0.42
     renovating
    0.41
     message
    0.40
     fundraising
    0.40
    Act Density 0.013%

    No Known Activations