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

    Neuronpedia

    INDEX
    Explanations

    step-by-step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    borderRadius
    1.03
    buff
    1.03
    tım
    1.02
    🧉
    1.00
     BorderRadius
    0.98
    titan
    0.96
    tipped
    0.96
     IMO
    0.96
    ec
    0.96
    Veteran
    0.96
    POSITIVE LOGITS
     Schritte
    1.62
     Steps
    1.51
     steps
    1.50
    一步
    1.49
    steps
    1.46
    驟
    1.42
     Step
    1.40
     adım
    1.37
    Steps
    1.36
    骤
    1.36
    Act Density 0.076%

    No Known Activations