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

    Neuronpedia

    INDEX
    Explanations

    companion or friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    غ
    0.61
    on
    0.51
    سي
    0.50
    ارة
    0.49
    الي
    0.48
    ية
    0.47
     Aquí
    0.47
     propietario
    0.46
     A
    0.45
     It
    0.44
    POSITIVE LOGITS
     companionship
    0.68
    companions
    0.63
     companions
    0.59
    し
    0.57
     ခ
    0.55
    fitted
    0.55
    moins
    0.54
    allergenic
    0.54
    sixth
    0.54
    companion
    0.53
    Act Density 0.217%

    No Known Activations