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

    Neuronpedia

    INDEX
    Explanations

    directory filepath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shears
    0.43
     reheat
    0.40
    лимп
    0.40
     influencers
    0.39
    ಮೇ
    0.38
     onTap
    0.37
     radiotherapy
    0.36
     veículos
    0.35
    illions
    0.35
    وب
    0.35
    POSITIVE LOGITS
     classpath
    0.57
    Classpath
    0.51
    path
    0.49
    getResource
    0.48
    加载
    0.47
     path
    0.46
     Resources
    0.46
    loader
    0.45
     filepath
    0.45
     filename
    0.44
    Act Density 0.193%

    No Known Activations