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

    Neuronpedia

    INDEX
    Explanations

    CapCut, binary image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Servers
    0.51
    Ziel
    0.47
    Tienes
    0.47
    Tor
    0.46
    Selamat
    0.46
    Surgery
    0.45
    Well
    0.45
    Regards
    0.44
    Telefon
    0.44
    Votre
    0.44
    POSITIVE LOGITS
     plan
    0.46
     inplace
    0.46
     evaporate
    0.46
    e
    0.44
     Plan
    0.43
     diff
    0.43
     avar
    0.42
     ruin
    0.41
    返回
    0.41
    하다
    0.41
    Act Density 0.000%

    No Known Activations