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

    Neuronpedia

    INDEX
    Explanations

    Identity and information categorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.47
    प
    0.44
     McKe
    0.44
    л
    0.44
    \|^{
    0.43
     palatable
    0.42
    ，
    0.42
     pale
    0.42
     anf
    0.42
     spiked
    0.41
    POSITIVE LOGITS
     类
    0.51
     미술
    0.51
    ation
    0.46
    ത്രി
    0.46
     مستقیم
    0.46
     항공
    0.46
     সঙ্গীতের
    0.45
     مساله
    0.45
    ôt
    0.45
     organisasi
    0.45
    Act Density 0.001%

    No Known Activations