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

    Neuronpedia

    INDEX
    Explanations

    option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ];
    0.38
    iftoire
    0.37
    éc
    0.37
    ević
    0.37
    iał
    0.37
    etheless
    0.36
    YAN
    0.35
    orno
    0.35
     খুশি
    0.34
     TOC
    0.34
    POSITIVE LOGITS
     computer
    0.63
     computers
    0.55
    computer
    0.54
    Computer
    0.54
     komputer
    0.54
     컴퓨터
    0.53
     compute
    0.53
     hardware
    0.52
    電腦
    0.52
     Computer
    0.51
    Act Density 0.149%

    No Known Activations