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

    Neuronpedia

    INDEX
    Explanations

    dark launching, dots, target task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    淙
    0.41
     disposiciones
    0.41
    เซ
    0.41
    Ь
    0.40
    કે
    0.39
    ը
    0.39
     jestem
    0.39
    ذية
    0.39
     কীর
    0.38
     डिटेल्स
    0.38
    POSITIVE LOGITS
    fer
    0.54
    flops
    0.45
     TVs
    0.43
    deleg
    0.42
    v
    0.42
    Ǧ
    0.41
    ag
    0.40
    erg
    0.40
    illos
    0.39
     productivity
    0.39
    Act Density 0.011%

    No Known Activations