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

    Neuronpedia

    INDEX
    Explanations

    mining and repair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    averaged
    0.41
    answered
    0.41
     kubectl
    0.41
    NAMEN
    0.40
    彧
    0.40
     നീ
    0.39
     далеко
    0.39
    っており
    0.39
    脖
    0.39
     fakult
    0.39
    POSITIVE LOGITS
     repairing
    0.40
    Mining
    0.39
    Repair
    0.38
     Mining
    0.38
    AddNew
    0.38
    льнявыя
    0.36
     utilising
    0.36
     mining
    0.35
     established
    0.35
     accessing
    0.35
    Act Density 0.000%

    No Known Activations