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

    Neuronpedia

    INDEX
    Explanations

    social-emotional learning or rooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fcm
    0.63
     dicha
    0.61
     Pública
    0.60
    Clinic
    0.57
    Rural
    0.55
    household
    0.55
    ﻪ
    0.55
    RBI
    0.54
    ＇
    0.54
    urgery
    0.53
    POSITIVE LOGITS
    ب
    0.57
     for
    0.54
     منشور
    0.51
     Its
    0.51
     приз
    0.51
     vesting
    0.49
     flagging
    0.49
     temperature
    0.49
     trillion
    0.49
    橹
    0.49
    Act Density 0.000%

    No Known Activations