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

    Neuronpedia

    INDEX
    Explanations

    can handle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    接近
    0.40
    􀂃
    0.40
    summar
    0.38
    %%
    0.38
    %,
    0.37
    charisma
    0.36
    を行
    0.36
    シャフト
    0.35
    scheduling
    0.35
    Scheduling
    0.35
    POSITIVE LOGITS
    噙
    0.40
     Futebol
    0.40
     firme
    0.39
     האל
    0.39
     Fußball
    0.38
    ɢ
    0.38
     investig
    0.38
    ว
    0.38
    Fragment
    0.37
     gạo
    0.37
    Act Density 0.000%

    No Known Activations