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

    Neuronpedia

    INDEX
    Explanations

    all of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefreshToken
    0.53
    グッズ
    0.50
    DCs
    0.48
     democracia
    0.47
    最大の
    0.46
     charlas
    0.46
     rumors
    0.46
     miejscowości
    0.46
    最も
    0.45
    مه
    0.45
    POSITIVE LOGITS
     together
    0.54
    atov
    0.50
     O
    0.48
     sammen
    0.47
     WITH
    0.47
     entire
    0.46
     вместе
    0.46
    Oo
    0.46
     пред
    0.45
    ~\
    0.45
    Act Density 0.004%

    No Known Activations