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

    Neuronpedia

    INDEX
    Explanations

    software libraries and frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kat
    0.44
     Kata
    0.43
     Kh
    0.41
     Sc
    0.40
     Soft
    0.40
     подума
    0.40
     Sophia
    0.39
     Sofia
    0.39
     Ansible
    0.39
     Khan
    0.38
    POSITIVE LOGITS
     zin
    0.45
     dầu
    0.42
     સેવા
    0.40
    クロマト
    0.40
    .(\
    0.38
    オイル
    0.38
    油
    0.37
    <unused1043>
    0.37
     paintball
    0.36
     масло
    0.35
    Act Density 0.000%

    No Known Activations