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

    Neuronpedia

    INDEX
    Explanations

    AI generation and simulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bidirectional
    0.48
    روش
    0.47
     are
    0.46
    数
    0.46
     IDs
    0.46
     EXPL
    0.45
     IAM
    0.45
     CRL
    0.45
     eps
    0.45
     সুতরাং
    0.44
    POSITIVE LOGITS
    aken
    0.46
    itters
    0.44
     nChar
    0.43
    itle
    0.42
    itt
    0.42
     heathen
    0.42
     bên
    0.41
    alen
    0.41
    pathTemplates
    0.41
    稷
    0.41
    Act Density 0.001%

    No Known Activations