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

    Neuronpedia

    INDEX
    Explanations

    phrases describing houses and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рган
    0.39
    éndose
    0.38
    没有人
    0.38
     Idea
    0.37
    ើញ
    0.37
    ढ़ी
    0.37
    ếng
    0.37
     মানুষ
    0.37
    ission
    0.36
     idea
    0.36
    POSITIVE LOGITS
     house
    0.63
     property
    0.60
    property
    0.57
     focal
    0.54
     ఇంటి
    0.54
     residence
    0.54
     propriété
    0.52
     propriedade
    0.49
     घर
    0.47
     impressive
    0.47
    Act Density 0.006%

    No Known Activations