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

    Neuronpedia

    INDEX
    Explanations

    recommendations and approvals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ायचे
    0.46
     transcribe
    0.43
    分からない
    0.42
    뀔
    0.41
     असतात
    0.40
     micrograph
    0.40
     Hints
    0.39
    ˏ
    0.39
    わからない
    0.38
    皤
    0.38
    POSITIVE LOGITS
     recommendation
    0.74
    Recommend
    0.69
     Recommendation
    0.68
     RECOMMEND
    0.68
     recommended
    0.67
     recommending
    0.67
    recommend
    0.66
    Recommendation
    0.65
     approved
    0.63
     approval
    0.62
    Act Density 0.008%

    No Known Activations