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

    Neuronpedia

    INDEX
    Explanations

    importance and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resembles
    0.40
     اسپ
    0.37
     aras
    0.37
    thane
    0.36
     smiles
    0.36
     мульти
    0.35
     euthanasia
    0.35
    于是
    0.35
    沿着
    0.35
     Alas
    0.35
    POSITIVE LOGITS
    Determin
    0.55
    主要的
    0.53
     фактор
    0.52
     determining
    0.51
     focus
    0.50
     viktig
    0.50
     najważ
    0.50
     fokus
    0.50
     أهم
    0.49
     foco
    0.48
    Act Density 0.084%

    No Known Activations