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

    Neuronpedia

    INDEX
    Explanations

    positive sentimentfavorable outcomespositive or favorable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সামরিক
    0.36
    ियो
    0.35
     সাধারণত
    0.35
    FilesIn
    0.34
    物理
    0.34
    github
    0.32
    在
    0.32
    依托
    0.31
     institutions
    0.31
    ếm
    0.31
    POSITIVE LOGITS
     positivos
    0.44
     vollständ
    0.43
    .
    0.41
     positiva
    0.39
     ganas
    0.39
     positivas
    0.39
     हराया
    0.39
     positive
    0.38
     மகிழ்ச்ச
    0.38
    avorable
    0.37
    Act Density 0.037%

    No Known Activations