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

    Neuronpedia

    INDEX
    Explanations

    personal services and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.56
    ᔨ
    0.49
    ゝ
    0.48
     "../../
    0.46
    -
    0.44
     regain
    0.42
    婇
    0.41
    한
    0.40
     والإ
    0.39
    棸
    0.39
    POSITIVE LOGITS
    INCRE
    0.52
    но
    0.50
    Biografia
    0.48
    новый
    0.47
    jego
    0.47
    фект
    0.46
    јединачна
    0.46
    новых
    0.46
    ிகளில்
    0.46
     повече
    0.46
    Act Density 0.000%

    No Known Activations